merged_output.json

{"wav": "Y7fmOlUlwoNg.wav", "ground_truth_captions": "A machine is making clicking sound as people talk in the background", "generated_captions": "There is the sound of an engine idling throughout the entire duration of the audio, and there's also a brief male voice speaking at the beginning."}
{"wav": "Y6BJ455B1aAs.wav", "ground_truth_captions": "A missile launching followed by an explosion and metal screeching as a motor hums in the background.", "generated_captions": "The audio contains sounds of explosions, gunshots, and artillery fire."}
{"wav": "YGOD8Bt5LfDE.wav", "ground_truth_captions": "A toy train running as a young boy talks followed by plastic clanking then a child laughing", "generated_captions": "There is a sound of steam hissing and people talking, specifically children speaking."}
{"wav": "YYQSuFyFm3Lc.wav", "ground_truth_captions": "Clattering of a train is ongoing, a railroad crossing bell rings, and a train horn blows", "generated_captions": "The audio contains the sound of a train moving on tracks, squealing wheels, and a horn blowing."}
{"wav": "YVjSEIRnLAh8.wav", "ground_truth_captions": "Food sizzling with some knocking and banging followed by a woman speaking", "generated_captions": "There is the sound of food sizzling, dishes clattering, and cutlery being used throughout the audio. Additionally, there is speech by both male and female speakers."}
{"wav": "YDlWd7Wmdi1E.wav", "ground_truth_captions": "A man talks while several animals make noises in the background", "generated_captions": "The audio contains sounds of birds, dogs, and ducks."}
{"wav": "YYNDKuNINDOY.wav", "ground_truth_captions": "An emergency siren ringing with car horn honking", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a police car siren, and background noise."}
{"wav": "YfsBR7e_X_0Y.wav", "ground_truth_captions": "An infant yelling as a young boy talks while a hard surface is slapped several times", "generated_captions": "There is a child speaking and crying, mechanisms sounds, and breathing heard throughout the audio."}
{"wav": "YtjCNwdOUiGc.wav", "ground_truth_captions": "A bus engine running followed by a bus horn honking", "generated_captions": "The audio contains sounds of a large motor vehicle engine running, wind blowing into the microphone, and water splashing."}
{"wav": "YyL3gKa6YLoM.wav", "ground_truth_captions": "A man speaking followed by snoring", "generated_captions": "There is a sound of someone snoring throughout the entire duration of the audio, and there's also a sound of breathing heard towards the end."}
{"wav": "YLbken4JCr94.wav", "ground_truth_captions": "Rolling thunder with lightning strikes", "generated_captions": "The audio contains the sounds of rain falling and thunder clapping."}
{"wav": "Y_xylo5_IiaM.wav", "ground_truth_captions": "A woman and a baby are having a conversation", "generated_captions": "There is a baby crying, a woman speaking, and television playing in the background throughout the entire duration of the audio."}
{"wav": "YsVYTOURVsQ0.wav", "ground_truth_captions": "Water trickling with man speaking", "generated_captions": "There is the sound of water running and splashing throughout the audio, as well as male speech at various intervals."}
{"wav": "YSmdj6JFB9MQ.wav", "ground_truth_captions": "Female speech, a toilet flushing and then more speech", "generated_captions": "There is the sound of water running from a faucet, and female speech."}
{"wav": "Yu84FiZ_omhA.wav", "ground_truth_captions": "Loud high humming and croaking sound", "generated_captions": "There is the sound of an electric toothbrush being used throughout the entire duration of the audio, and there's also background noise present from 9.81 to 10 seconds."}
{"wav": "Ykx6Rj4MDIAw.wav", "ground_truth_captions": "A cuckoo bird coos followed by a train running on railroad tracks as a bell dings in the background", "generated_captions": "The audio contains the sound of a bell ringing, specifically a change ringing performance on bells, and the sound of birds chirping."}
{"wav": "YPLHXGDnig4M.wav", "ground_truth_captions": "A man talking then meowing and hissing", "generated_captions": "The audio contains mechanisms, breathing sounds, and male speech."}
{"wav": "YZ0IrCa4MvOA.wav", "ground_truth_captions": "Water flowing through pipes", "generated_captions": "There is the sound of water running from a faucet throughout the entire clip, and there's also background noise."}
{"wav": "Y14ekd4nkpwc.wav", "ground_truth_captions": "An infant crying followed by a man laughing", "generated_captions": "There is crying, babbling, and breathing sounds throughout the audio."}
{"wav": "YyfYNPWs7mWY.wav", "ground_truth_captions": "A man speaking, followed by a door shutting, and then the man speaks some more", "generated_captions": "The audio contains speech, breathing sounds, and background noise."}
{"wav": "YuhSDBwVrEdo.wav", "ground_truth_captions": "The wind is blowing, and a person is whistling a tune", "generated_captions": "The audio contains whistling sounds throughout its duration, accompanied by wind noise and faint rustling noises."}
{"wav": "YYQGW5AwDOIo.wav", "ground_truth_captions": "Motor vehicles are driving with loud engines and a person whistles", "generated_captions": "The audio contains the sound of a car accelerating and revving, along with other vehicle noises."}
{"wav": "YMe4npKmtchA.wav", "ground_truth_captions": "Bubbles gurgling and water spraying as a man speaks softly while crowd of people talk in the background", "generated_captions": "There is the sound of water running and splashing, as well as male speech throughout most of the audio clip."}
{"wav": "YgbtcDoh0q3c.wav", "ground_truth_captions": "Metal clacking followed by a man talking then a metal bang as footsteps shuffle on dirt and a group of men laugh", "generated_captions": "There is a cap gun firing, laughter, and conversation between male and female speakers."}
{"wav": "Y9HVgYs8OOLc.wav", "ground_truth_captions": "A man talking then a young boy talking followed by a loud pop as pigeons coo and bird wings flap", "generated_captions": "The audio contains sounds of pigeons cooing, birds flapping their wings, and people speaking."}
{"wav": "YOpiWMltpj44.wav", "ground_truth_captions": "Ducks quack and water splashes with some animal screeching in the background", "generated_captions": "There is the sound of water splashing and ducks quacking throughout the entire duration of the audio, from 0 to 10 seconds."}
{"wav": "Y9ZZHvwaH-CU.wav", "ground_truth_captions": "Multiple gun shots woman screaming", "generated_captions": "There is a machine gun firing, followed by a man speaking and then another machine gun firing."}
{"wav": "YK_Vre_-4KqU.wav", "ground_truth_captions": "An aircraft engine runs and vibrates, metal spinning and grinding occur, and the engine accelerates and fades into the distance", "generated_captions": "The audio contains the sound of an aircraft engine running and accelerating, along with wind blowing into a microphone."}
{"wav": "YqeSl7YZAfs4.wav", "ground_truth_captions": "A man is talking as tap water is running", "generated_captions": "There is the sound of water running from a faucet and a man speaking throughout the entire duration of the audio."}
{"wav": "Y4IeDBwyQ9ZQ.wav", "ground_truth_captions": "Woman speaking, plastic container opening", "generated_captions": "The audio contains speech, breathing sounds, and background noise."}
{"wav": "YArHiac57pVk.wav", "ground_truth_captions": "A male speaking", "generated_captions": "The audio contains speech by multiple speakers, specifically male speech and female speech."}
{"wav": "YqZEIs6tS5vk.wav", "ground_truth_captions": "A vehicle engine revving followed by tires skidding as a group of people talk in the background", "generated_captions": "The audio contains the sound of a car accelerating and tires squealing, which is categorized as vehicle sounds."}
{"wav": "Ypaf0nyjg1Js.wav", "ground_truth_captions": "A woman talking followed by a plate rattling as food and oil sizzle", "generated_captions": "There is the sound of food sizzling and frying, along with female speech throughout the audio."}
{"wav": "YBZCEDkx37rI.wav", "ground_truth_captions": "Humming of an idling engine", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "YFR7BDRhMATo.wav", "ground_truth_captions": "A train running on railroad tracks as a train horn whistle blows several times while railroad crossing warning signals are ringing", "generated_captions": "The audio contains the sound of a train moving and blowing its horn."}
{"wav": "YXJba7pTbpD0.wav", "ground_truth_captions": "Several varying hisses", "generated_captions": "There is the sound of steam hissing throughout the entire duration of the audio, and there's also the sound of water dripping from 9.78 to 10.0 seconds."}
{"wav": "YCeRoaEcqUgM.wav", "ground_truth_captions": "A motorboat driving by as water splashes followed by wind blowing into a microphone", "generated_captions": "The audio contains the sound of water splashing and gurgling, along with wind blowing into a microphone."}
{"wav": "Yzq00Oe1ecpE.wav", "ground_truth_captions": "A bus engine slowing down then accelerating", "generated_captions": "The audio contains sounds of wind blowing, traffic passing by, and an engine running."}
{"wav": "YztSjcZNUY7A.wav", "ground_truth_captions": "A woman talks as a baby cries", "generated_captions": "There is a baby crying and babbling, a woman speaking, and background noise throughout the entire duration of the audio."}
{"wav": "YglAeihz0NAM.wav", "ground_truth_captions": "Kids laughing then talking followed by a young man talking as wind blows into a microphone", "generated_captions": "There is speech, laughter, wind noise, and the sound of a bicycle or tricycle throughout the audio."}
{"wav": "YCM49C3RkzV8.wav", "ground_truth_captions": "A woman delivers a speech", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YH-vTZh81qAU.wav", "ground_truth_captions": "Clicking followed by humming noise", "generated_captions": "There is a clicking noise throughout the audio, and there's also white noise in the background."}
{"wav": "Yup2PpjTzyyc.wav", "ground_truth_captions": "Electronic beeping followed by a cat singing then meowing as paper shuffles and a man talks with music playing in the background", "generated_captions": "There is a cat meowing, a dog whimpering and barking, mechanisms sounds, and a woman speaking."}
{"wav": "YdlsiellSFf0.wav", "ground_truth_captions": "A high frequency motor hums loudly and splashes water", "generated_captions": "There is the sound of an engine running throughout the entire clip, and there's also the sound of wood being sawed from 9.78 to 10.00 seconds."}
{"wav": "Y0jGH7A_hpBM.wav", "ground_truth_captions": "An adult male speaks, followed by another adult male speaking", "generated_captions": "The audio contains sounds of waves, surf, and wind."}
{"wav": "YCefFMA3klxk.wav", "ground_truth_captions": "A horn and then an engine revving", "generated_captions": "The audio contains the sound of a train horn blowing and a vehicle passing by."}
{"wav": "YKnXNy5Q6YS4.wav", "ground_truth_captions": "Man speaking while insects buzz around", "generated_captions": "The audio contains sounds of birds chirping, wind blowing, and water flowing."}
{"wav": "YcPiSd5nJLrI.wav", "ground_truth_captions": "Screaming and a big explosion and then screaming", "generated_captions": "There is a dog barking and growling, human sounds of breathing, and generic impact sounds throughout the audio."}
{"wav": "YrJVXE6Axtrg.wav", "ground_truth_captions": "A man speaks and a machine runs with a continued speech", "generated_captions": "There is a sound of an electric toothbrush and mechanisms throughout the entire duration, along with male speech starting from 10 seconds to almost 14 seconds."}
{"wav": "YFA11v4SmdBc.wav", "ground_truth_captions": "Man speaks followed by whistling", "generated_captions": "The audio contains speech by a male speaker, and background noise throughout the entire duration of the recording."}
{"wav": "Y3iLGu2Omgrw.wav", "ground_truth_captions": "A man speaking", "generated_captions": "The audio contains speech by a male speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YQvATUKXYFBs.wav", "ground_truth_captions": "Warning bells ring and a train passes with a honking horn", "generated_captions": "The audio contains the sound of a train horn blowing and a train passing by."}
{"wav": "Y_ezm-TpKj1w.wav", "ground_truth_captions": "Humming of a revving idling engine with people speaking in the distance", "generated_captions": "The audio contains sounds of an engine revving, accelerating, and vrooming, as well as male speech."}
{"wav": "Yq46VXJ6JN9M.wav", "ground_truth_captions": "Birds are chirping in the background, rustling and clattering ensue, then a hissing spray and more rustling and clattering occur", "generated_captions": "There is the sound of a spray being released throughout the audio, and there's also the sound of something being tapped on a surface."}
{"wav": "YYEYeQ0lIkBQ.wav", "ground_truth_captions": "A man talking then laughing as a ducks quack", "generated_captions": "There is a sound of water splashing, ducks quacking, and people talking and laughing."}
{"wav": "Y31WGUPOYS5g.wav", "ground_truth_captions": "The buzz of the crowd is interrupted by a child shouting, followed by a police siren and a horn honking", "generated_captions": "There is a truck horn honking, people talking and cheering, and a bell ringing."}
{"wav": "YKtTLsveexOg.wav", "ground_truth_captions": "A sewing machine running as a steam hisses followed by a machine motor sharply running in the background", "generated_captions": "There is the sound of an engine idling throughout the entire duration of the audio, and towards the end there is a brief moment where something is being tapped."}
{"wav": "Y5QZ0NtdoKJ8.wav", "ground_truth_captions": "Continuous digital beeps with a person speaking and bird chirping in the background", "generated_captions": "There is a man speaking and birds chirping throughout the audio."}
{"wav": "Y_AcJVyToQUQ.wav", "ground_truth_captions": "Laughter and a female speaking and then a male vocalizing a sneezing sound", "generated_captions": "There is laughter, breathing sounds, and male speech throughout the audio."}
{"wav": "YkEP-BwMarf8.wav", "ground_truth_captions": "A wrapper crinkling and a woman's soft voice", "generated_captions": "The audio contains the sound of paper crumpling and crinkling."}
{"wav": "YyVVLq4ao1Ck.wav", "ground_truth_captions": "Insects trill in the background, while birds chirp and flies buzz", "generated_captions": "There is the buzzing of insects, chirping birds, and a woman laughing."}
{"wav": "YS0YE96w0YRk.wav", "ground_truth_captions": "A man speaking followed by a crowd of people laughing then applauding", "generated_captions": "The audio contains sounds of clapping, cheering, and shouting from the crowd, as well as male speech."}
{"wav": "Ylh801oHGtD4.wav", "ground_truth_captions": "A man talking as an electronic device hums followed by a door closing", "generated_captions": "There is a man speaking, mechanisms and surface contact sounds, and generic impact sounds throughout the audio."}
{"wav": "YPb6MqpdX5Jw.wav", "ground_truth_captions": "A horse gallops then trot on grass as gusts of wind blow and thunderclaps in the distance", "generated_captions": "The audio contains wind noise, clip-clop sounds of a horse trotting, and generic impact sounds."}
{"wav": "Y9U8COLzEegs.wav", "ground_truth_captions": "Water running softly in the background followed by several shrill beeps and a man speaking", "generated_captions": "There is the sound of water running and dripping, along with male speech."}
{"wav": "Ydxow2DcTrwk.wav", "ground_truth_captions": "A man and a woman talking while rain falls, followed by a crash of thunder", "generated_captions": "The audio contains rain falling on a surface, wind blowing into a microphone, and male speech."}
{"wav": "Ya0yXS7PmVR0.wav", "ground_truth_captions": "Praying with mechanical noise in background", "generated_captions": "The audio contains the sound of an engine idling and a man singing."}
{"wav": "Y0a9wVat2PWk.wav", "ground_truth_captions": "A train sounds horn and travels", "generated_captions": "The audio contains sounds of a train horn blowing and wind blowing into the microphone."}
{"wav": "Ybgbnu5YKTDg.wav", "ground_truth_captions": "A man is speaking followed by gunfire", "generated_captions": "The audio contains speech, background noise, and the sound of typing on a computer keyboard."}
{"wav": "YCO6-i8NLbeo.wav", "ground_truth_captions": "A man talking followed by a goat baaing then a metal gate sliding shut as ducks quack and wind blows into a microphone", "generated_captions": "The audio contains sounds of wind, bird vocalizations, and horse trotting."}
{"wav": "YpI_kPedctoo.wav", "ground_truth_captions": "An engine running and being revved and some muffled speech", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with medium engine sounds throughout."}
{"wav": "YEYTz1LPDHsc.wav", "ground_truth_captions": "A car door opening as a crow caws and birds chirp followed by a vehicle driving by in the background", "generated_captions": "The audio contains sounds of birds chirping, ducks quacking, and water splashing."}
{"wav": "YD9tinq3RMpU.wav", "ground_truth_captions": "A large motor is running smoothly, water is splashing, people are talking in the background, and an adult male speaks in the distance", "generated_captions": "There is the sound of water rushing by, and people talking in the background throughout the entire duration of the audio."}
{"wav": "YEzWEO2WD_MM.wav", "ground_truth_captions": "High frequency humming followed by a smack", "generated_captions": "There is the sound of a hair dryer running throughout the audio, and there's also the sound of water splashing at the beginning."}
{"wav": "YtfOIhQpYYe8.wav", "ground_truth_captions": "A helicopter flying as a man talks in the background", "generated_captions": "There is the sound of an engine idling and a man speaking throughout the entire duration of the audio."}
{"wav": "Y_w2pA1VeB40.wav", "ground_truth_captions": "Continuous laughter", "generated_captions": "There is a baby crying and laughing, and there's also background noise throughout the entire clip."}
{"wav": "YJnSwRonB9wI.wav", "ground_truth_captions": "A muffled motorboat engine running as a group of people are laughing and screaming while water splashes and sprays", "generated_captions": "There is laughter, wind noise on the microphone, water splashing and gurgling sounds throughout the audio."}
{"wav": "YRNBoH2LHQEM.wav", "ground_truth_captions": "A crowd of people applauding", "generated_captions": "The audio contains the sound of an audience applauding, which is categorized as human sounds and applause."}
{"wav": "YpaetCbEqp2w.wav", "ground_truth_captions": "Some light tapping on a computer keyboard and a baby crying", "generated_captions": "The audio contains the ticking of a clock and white noise throughout its duration."}
{"wav": "YLs1zyPjs3k8.wav", "ground_truth_captions": "A bleeping noise followed by a static noise", "generated_captions": "The audio contains the sound of an electric toothbrush being used, and there is also background noise throughout the entire clip."}
{"wav": "YK03ydb1uaoQ.wav", "ground_truth_captions": "Static sounds are vibrating along with snoring", "generated_captions": "There is snoring and breathing sounds throughout the entire duration of the audio, with intermittent impact sounds occurring at various intervals."}
{"wav": "Yific_gRalg0.wav", "ground_truth_captions": "A series of loud metal hammering as liquid drains down a pipe followed by a metal chain rattling", "generated_captions": "The audio contains the sounds of water dripping and trickling, followed by the sound of something being crushed or broken."}
{"wav": "YBlbGXalLNVU.wav", "ground_truth_captions": "Surf comes ashore as a man speaks", "generated_captions": "The audio contains the sounds of waves, surf, and wind blowing into a microphone."}
{"wav": "Y1nUOGZgSzZo.wav", "ground_truth_captions": "Water is splashing and a man laughs", "generated_captions": "There is the sound of water splashing and gurgling throughout, along with female speech and laughter."}
{"wav": "Yc0V_HAul7rI.wav", "ground_truth_captions": "People laugh and speak", "generated_captions": "There is background noise throughout the entire clip, and there's laughter from both male and female speakers at various intervals."}
{"wav": "YPtW0cZVprJQ.wav", "ground_truth_captions": "Snoring followed by male speech", "generated_captions": "There is snoring, breathing sounds, and mechanisms throughout the entire duration of the audio."}
{"wav": "YAbplcXwXnvE.wav", "ground_truth_captions": "Female speaking followed by crinkling", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "Yd1tL-9BILy8.wav", "ground_truth_captions": "Pigeons cooing followed by camera muffling", "generated_captions": "The audio contains the sounds of birds cooing and flapping their wings, as well as generic impact sounds."}
{"wav": "YonBZOH88OYs.wav", "ground_truth_captions": "Repeated bursts of spray", "generated_captions": "There is the sound of a drill running throughout the entire clip, and there's also the sound of something being sprayed from 9:78 to 10:00."}
{"wav": "Y3wV3ST-c4PE.wav", "ground_truth_captions": "Tick-tocking by a clock", "generated_captions": "The audio contains the ticking of a clock and mechanisms sounds throughout its duration."}
{"wav": "Yy93cZqNCtks.wav", "ground_truth_captions": "A man talking as footsteps run on concrete followed by a series of gunshots firing a gun cocking while another man talks in the background before a dog growls", "generated_captions": "The audio contains sounds of mechanisms, wind, and generic impact sounds."}
{"wav": "YL2dyilgQ8iM.wav", "ground_truth_captions": "Muffled rustling noise over wind blowing over a microphone", "generated_captions": "The audio contains wind noise and the sound of water splashing."}
{"wav": "YWWkhzcmx3VE.wav", "ground_truth_captions": "A duck quacking", "generated_captions": "The audio contains bird chirping and tweeting sounds, along with the sound of water flowing."}
{"wav": "Yu9px4Lwv9XI.wav", "ground_truth_captions": "Footsteps and a croaking frog", "generated_captions": "The audio contains sounds of ducks quacking, birds chirping and singing, water splashing, and wind blowing."}
{"wav": "Yhrv6fwnmBkY.wav", "ground_truth_captions": "A dog whimpering followed by laughing and barking.", "generated_captions": "There is a dog barking and growling, and there is also a woman speaking."}
{"wav": "YzEaGx6an4es.wav", "ground_truth_captions": "A sustained and coarse drilling noise", "generated_captions": "There is the sound of a power tool drilling and mechanisms working throughout the entire duration of the audio clip from 0 to 10 seconds."}
{"wav": "YE6FH_xp3I54.wav", "ground_truth_captions": "A man is speaking followed by birds chirping", "generated_captions": "The audio contains the sounds of crickets chirping and insects buzzing, along with male speech."}
{"wav": "YDt53UZgyznE.wav", "ground_truth_captions": "Baby cries and then man speaks", "generated_captions": "There is crying, breathing sounds, and mechanisms throughout the entire duration of the audio."}
{"wav": "YOMGHnJV0l2U.wav", "ground_truth_captions": "Scraping and banging", "generated_captions": "The audio contains the sound of typing on a typewriter and mechanisms."}
{"wav": "Y-NsC63dA01g.wav", "ground_truth_captions": "An adult female speaks as a cat meows three times, and an electronic device plays in the background", "generated_captions": "The audio contains sounds of mechanisms, child speech, crying, and breathing."}
{"wav": "YfGGYeXR_LS8.wav", "ground_truth_captions": "Whistling is ongoing while an adult male speaks, and water is pattering in the background", "generated_captions": "There is whistling, mechanisms, and male speech throughout the entire duration of the audio."}
{"wav": "YhJtOGmN_KVw.wav", "ground_truth_captions": "Plastic crinkling and paper sliding as a man talks", "generated_captions": "There is crumpling and crinkling sounds, mechanisms, and male speech throughout the audio."}
{"wav": "YUmNrhFKpWIY.wav", "ground_truth_captions": "A car engine revs and then shuts off", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with generic impact sounds."}
{"wav": "YxBZnvfniA1c.wav", "ground_truth_captions": "A man speaks, and a child speaks followed by laughter", "generated_captions": "There is a child speaking, laughter, and sounds of mechanisms throughout the audio."}
{"wav": "YEQVWhHmT_cE.wav", "ground_truth_captions": "A male speaking and the glass shattering followed by a laughter", "generated_captions": "There is speech, laughter, and breathing sounds throughout the audio."}
{"wav": "YUCy1BEx8jBE.wav", "ground_truth_captions": "A man speaking as a stream of water sprays and splashes", "generated_captions": "The audio contains the sounds of water running and gurgling, as well as male speech."}
{"wav": "YF7QtqKtllK0.wav", "ground_truth_captions": "A person snores", "generated_captions": "There is snoring and breathing sounds throughout the audio, with background noise of mechanisms."}
{"wav": "YalaxBd_EEUc.wav", "ground_truth_captions": "A man speaks briefly followed by a succession of several eructations", "generated_captions": "There is speech throughout the entire duration of the audio, and there's also a groan heard from 6.92 to 7.58 seconds."}
{"wav": "YGSHcgY6ATkQ.wav", "ground_truth_captions": "A man speaking followed by typing on a keyboard", "generated_captions": "The audio contains speech and breathing sounds."}
{"wav": "YxYwpABpZed4.wav", "ground_truth_captions": "A woman speeches while cooks", "generated_captions": "The audio contains the sounds of rain and thunder, as well as female speech."}
{"wav": "YlfO471Rn61k.wav", "ground_truth_captions": "Steam escapes with a hissing noise", "generated_captions": "There is the sound of a drill being used throughout the entire duration of the audio, and there's also the sound of steam hissing from 10 seconds to almost 12 seconds into the recording."}
{"wav": "YHZ9O6sc7cLA.wav", "ground_truth_captions": "A woman speaks followed by a dog barking", "generated_captions": "The audio contains speech, breathing sounds, and surface contact noises."}
{"wav": "Y41D0yXSBqfI.wav", "ground_truth_captions": "Pigeons cooing and bird wings flapping while gravel shuffles and wood clacks", "generated_captions": "The audio contains the sounds of birds cooing and flapping their wings, specifically pigeons."}
{"wav": "YJ0yeFeKvIt8.wav", "ground_truth_captions": "Wind blowing and leaves rustling followed by plastic clicking and wind blowing into a microphone", "generated_captions": "The audio contains wind noise, rustling leaves, and the sound of water flowing."}
{"wav": "YKvrcRMfFzOE.wav", "ground_truth_captions": "A helicopter is in flight with loud blades moving fast", "generated_captions": "The audio contains the sound of an aircraft engine idling and running, specifically a helicopter."}
{"wav": "Y7cHRSfbp7tc.wav", "ground_truth_captions": "A group of people talking as dishes clack followed by wood knocking", "generated_captions": "The audio contains sounds of dishes, pots, and pans clanging, mechanisms, and male speech."}
{"wav": "YNeWW30WZjPc.wav", "ground_truth_captions": "A dog barks and rustles with some clicking", "generated_captions": "There is a dog barking and growling throughout the entire duration of the audio, with some background noise also present."}
{"wav": "YdYvL6uEMl6E.wav", "ground_truth_captions": "A helicopter flying followed by wind heavily blowing into a microphone", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "YjjHIINDfE1c.wav", "ground_truth_captions": "A tractor driving by as a car horn honks while wind blows into a microphone", "generated_captions": "The audio contains sounds of a train, including its horn and wheels squealing on the tracks."}
{"wav": "YsqsI2UyrcBQ.wav", "ground_truth_captions": "A vehicle engine accelerating and revving", "generated_captions": "The audio contains sounds of a car accelerating and revving, along with generic impact sounds."}
{"wav": "YjOYvIISk--4.wav", "ground_truth_captions": "A man speaking followed by a faucet turning on and off while pouring water twice proceeded by water draining down a pipe", "generated_captions": "There is a man speaking, water running from faucet to sink, and mechanisms sounds throughout the audio."}
{"wav": "Y3MoF8myFs8Y.wav", "ground_truth_captions": "A strong wind is blowing and constant background waves can be heard", "generated_captions": "The audio contains the sounds of waves, surf, wind noise (microphone), and water."}
{"wav": "YPMMkPq5jJXY.wav", "ground_truth_captions": "A person burps as people laugh", "generated_captions": "There is a loud burp followed by laughter, and then another burp."}
{"wav": "YAtkD-3GjXMw.wav", "ground_truth_captions": "Singing and music with faint gunshots", "generated_captions": "The audio contains video game sounds, music, and sound effects including gunshots, explosions, and a whooshing noise."}
{"wav": "Y6Nvu6EcpdE8.wav", "ground_truth_captions": "Wind blows and a man speaks with a quick pop", "generated_captions": "The audio contains wind noise, waves crashing, and the sound of water splashing."}
{"wav": "YzoxFl3pddMg.wav", "ground_truth_captions": "A frog chirping with distant speaking of a person", "generated_captions": "The audio contains the sounds of frogs croaking and insects chirping."}
{"wav": "YVQnmlf2OsUg.wav", "ground_truth_captions": "A toy helicopter flying", "generated_captions": "There is the sound of a small engine running throughout the entire duration of the audio, and there's also the sound of steam hissing from 9.85 to 10 seconds."}
{"wav": "YB4SZwi9Ce3o.wav", "ground_truth_captions": "A man talking and plastic clicking as a vehicle engine accelerates", "generated_captions": "The audio contains sounds of mechanisms, generic impact sounds, and surface contact, as well as male speech."}
{"wav": "Y9ucb5HYO8ps.wav", "ground_truth_captions": "A burp followed by laughter and speech", "generated_captions": "There is a loud burp followed by laughter and conversation, with background noise throughout the entire clip."}
{"wav": "YNJEPbGVBJIQ.wav", "ground_truth_captions": "A man speaks followed by a vehicle revving", "generated_captions": "The audio contains sounds of mechanisms, accelerating - revving - vroom, and male speech."}
{"wav": "YZYWCwfCkBp4.wav", "ground_truth_captions": "Rustling and sanding on wood with distant music playing", "generated_captions": "There is a sound of something being sprayed throughout the entire duration of the audio, and there's also a generic impact sound occurring at some point during it."}
{"wav": "Y9XqkKuTqEOM.wav", "ground_truth_captions": "Some rustling and scratching with a short click", "generated_captions": "The audio contains sounds of mechanisms, generic impact sounds, and crumpling or crinkling noises."}
{"wav": "Y3IguMJkqpl4.wav", "ground_truth_captions": "People speaking followed by a duck quacking and a child crying", "generated_captions": "The audio contains sounds of chickens and roosters, human voices, laughter, and water splashing."}
{"wav": "YUhCzD6EBJBU.wav", "ground_truth_captions": "A power tool drilling followed by metal clacking then a man talking proceeded by a door closing shut", "generated_captions": "There is a man speaking, mechanisms and tools sounds, and a power tool drilling."}
{"wav": "YTQr9v-PQOc4.wav", "ground_truth_captions": "A person sneezes and coughs", "generated_captions": "There is a sound of someone laughing and coughing, along with background noise throughout the entire duration of the audio."}
{"wav": "Y0NGSrwioYjA.wav", "ground_truth_captions": "A man speaking followed by a goat baaing", "generated_captions": "There is a man speaking, birds chirping and singing, water splashing, and wind blowing throughout the audio."}
{"wav": "Y6Pywt0f_NFY.wav", "ground_truth_captions": "Water trickling as a machine hums in the background followed by water spraying", "generated_captions": "There is the sound of water running from a faucet and gurgling, along with mechanisms sounds throughout the entire duration of the audio."}
{"wav": "Yh5_1pnkl_SY.wav", "ground_truth_captions": "Middle aged man speaks foreign language while water is trickling", "generated_captions": "The audio contains the sounds of water, specifically a bathtub filling and running, as well as male speech."}
{"wav": "Yfx4r_KuW6No.wav", "ground_truth_captions": "Adult female is speaking and a young child is crying", "generated_captions": "There is a child singing and speaking, accompanied by background noise throughout the entire duration of the audio."}
{"wav": "Y9F3sutgYTvo.wav", "ground_truth_captions": "A man is speaking and a baby whimpers followed by a woman talking", "generated_captions": "There is a baby crying and babbling, a woman speaking, and mechanisms sounds throughout the audio."}
{"wav": "Y7P6lcyeDKNI.wav", "ground_truth_captions": "A bicycle peddling on dirt and gravel followed by a man speaking then laughing", "generated_captions": "There is laughter, speech, and the sound of rain falling on a surface throughout the audio."}
{"wav": "YQHfyKaOHSz4.wav", "ground_truth_captions": "A fly buzzing and a frog croaking with musical sounds", "generated_captions": "There is the buzzing of insects and birds chirping throughout the audio, with intermittent sounds of bees or wasps buzzing."}
{"wav": "YSE_3nszEw7o.wav", "ground_truth_captions": "Hissing and clinking", "generated_captions": "There is the sound of spraying and hissing throughout the entire duration of the audio, along with background noise."}
{"wav": "Y_iUX8CibElk.wav", "ground_truth_captions": "Humming sounds from a distance", "generated_captions": "The audio contains the sound of an engine idling and then revving up, as well as the sound of water splashing."}
{"wav": "Y2JutOgAnqWA.wav", "ground_truth_captions": "A tool motor is running, a rattling sound occurs, then humming also, then soft squealing occurs", "generated_captions": "There is the sound of a power tool drilling and a mechanism working throughout the entire duration of the audio."}
{"wav": "YbX2vDaHL26U.wav", "ground_truth_captions": "A car skidding its tires and racing away", "generated_captions": "The audio contains sounds of race car engines revving and tires squealing, along with male speech."}
{"wav": "YXf5LjaE_JQ0.wav", "ground_truth_captions": "Traffic sounds going by as man speaks", "generated_captions": "The audio contains sounds of mechanisms, wind, and male speech."}
{"wav": "YCh0LMmhBUg4.wav", "ground_truth_captions": "A man speaks with some distant hum and a child speaking", "generated_captions": "The audio contains sounds of mechanisms, generic impact sounds, and surface contact."}
{"wav": "Yl5KdHAWwJCw.wav", "ground_truth_captions": "Ticking of a clock", "generated_captions": "The audio contains the ticking of a clock and mechanisms sounds throughout its duration."}
{"wav": "YVE6Ku0-ucUM.wav", "ground_truth_captions": "A man speaks followed by a popping noise and laughter", "generated_captions": "The audio contains laughter, speech, and breathing sounds."}
{"wav": "YYIqpIjjee00.wav", "ground_truth_captions": "A flush occurs with water splashing and gurgling, and then water runs steadily", "generated_captions": "There is the sound of water running from a faucet and splashing into a sink throughout the entire duration of the audio, as well as generic impact sounds occurring at various intervals."}
{"wav": "YItS07xtdi4s.wav", "ground_truth_captions": "Fire igniting as a motor runs followed by an electronic beep and vehicle engines running idle then car horns honking", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with the sounds of wind blowing into a microphone."}
{"wav": "YHeEa1GZpUGI.wav", "ground_truth_captions": "Several gunshots followed by a click and glass breaking", "generated_captions": "The audio contains the sounds of gunfire, machine gun fire, and wind blowing into a microphone."}
{"wav": "YjjfUaMQaG1A.wav", "ground_truth_captions": "A man talking followed by plastic clacking then a power tool drilling", "generated_captions": "There is the sound of a power tool drilling and a man speaking throughout the duration of the audio."}
{"wav": "Y79XDcI6xZm0.wav", "ground_truth_captions": "A crowd chants, an adult male speaks in the foreground, a member of the crowd shouts, and the adult male continues to speak", "generated_captions": "The audio contains battle cries and shouts from a crowd of people."}
{"wav": "Y52IxrdTxGs4.wav", "ground_truth_captions": "An explosion and heart beating as instrumental music plays followed by a man talking", "generated_captions": "The audio contains the sounds of explosions and artillery fire."}
{"wav": "YlJayhiVzl_E.wav", "ground_truth_captions": "Humming and rumbling of a powerful engine with wind blowing", "generated_captions": "The audio contains the sound of an engine accelerating and revving, idling, and medium frequency sounds."}
{"wav": "YgQMTOKsCIyk.wav", "ground_truth_captions": "A group of birds chirping and ducks quacking followed by a man speaking", "generated_captions": "There is a man speaking, birds chirping and tweeting, and a duck quacking throughout the audio."}
{"wav": "YLs2vrr9TamU.wav", "ground_truth_captions": "Drilling and crackling", "generated_captions": "There is the sound of a machine motor running and vibrating throughout the entire duration of the audio, along with the sound of wood being sawed."}
{"wav": "Y4SZ7JXDCNps.wav", "ground_truth_captions": "A car engine revving", "generated_captions": "The audio contains the sound of an engine revving and accelerating, specifically a medium engine (mid frequency)."}
{"wav": "YzIgGMlZENTs.wav", "ground_truth_captions": "A duck quacks followed by a man talking", "generated_captions": "The audio contains sounds of ducks quacking, water splashing and gurgling, and a man speaking."}
{"wav": "Y1GgEpRZDWN0.wav", "ground_truth_captions": "A man and woman speak", "generated_captions": "The audio contains speech by a male speaker and background noise."}
{"wav": "YqF72bT878gw.wav", "ground_truth_captions": "Humming from an engine with wind blowing hard", "generated_captions": "The audio contains the sound of an aircraft engine idling and then revving up, along with wind blowing into a microphone."}
{"wav": "YrgrmLLhxoCQ.wav", "ground_truth_captions": "Repeated scraping on two different surfaces", "generated_captions": "There is the sound of sanding wood and mechanisms throughout the entire duration of the audio, from 0 to 10 seconds."}
{"wav": "YVeCSHwtkBZU.wav", "ground_truth_captions": "A police siren going off", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a police car siren."}
{"wav": "YZ1Cyj4N05lk.wav", "ground_truth_captions": "Whistling with small rustling and groaning", "generated_captions": "The audio contains the sound of someone whistling and blowing into something, possibly a musical instrument or a whistle."}
{"wav": "YXplKBvZaHXA.wav", "ground_truth_captions": "A man talking as a motorbike engine revs and accelerates", "generated_captions": "The audio contains sounds of motorcycles revving and accelerating, as well as male speech."}
{"wav": "Yhzn_wGlzGpU.wav", "ground_truth_captions": "An aircraft engine accelerating followed by an object clanking against fiberglass as an emergency siren sounds in the background", "generated_captions": "There is an aircraft engine running throughout the audio, and there's also wind blowing into a microphone."}
{"wav": "Y0yxEvdnimGg.wav", "ground_truth_captions": "Dogs are barking with wind noise while people are speaking", "generated_captions": "There is a dog barking and whimpering, wind blowing into the microphone, and people talking."}
{"wav": "YLKhokVsJhN0.wav", "ground_truth_captions": "A flock of sheep baaing", "generated_captions": "There is wind blowing, birds chirping and singing, and sheep bleating throughout the audio."}
{"wav": "YRp4Ct_TQvAM.wav", "ground_truth_captions": "Rain falling as a machine motor runs followed by a man speaking", "generated_captions": "The audio contains the sounds of rain falling and a man speaking."}
{"wav": "YYqYCDis3EUA.wav", "ground_truth_captions": "The chirping of birds, interrupted by a rustling sound, and a buzzing fly", "generated_captions": "There is wind blowing, birds chirping and tweeting throughout the entire duration of the audio."}
{"wav": "YXL8JV9qXGLE.wav", "ground_truth_captions": "An infant whimpering and distant speech and brief laughter", "generated_captions": "There is crying, babbling, and breathing sounds throughout the audio."}
{"wav": "Y9BGLAUSF0sk.wav", "ground_truth_captions": "An idling engine humming non stop", "generated_captions": "There is an engine idling throughout the entire duration of the audio, and there's also some background noise."}
{"wav": "Y_duNX6Vyd6g.wav", "ground_truth_captions": "A motorboat drives on water quickly", "generated_captions": "There is the sound of an aircraft engine idling throughout the entire duration of the audio, and there's also the sound of wind blowing into a microphone at various intervals."}
{"wav": "Y7QN3lwOzfdg.wav", "ground_truth_captions": "An adult speaks over a telephone and then an adult male speaks, and this pattern repeats three times", "generated_captions": "The audio contains speech and background noise throughout its duration, with the presence of breathing sounds at specific intervals."}
{"wav": "YOUUckswAaNI.wav", "ground_truth_captions": "Male speaking and birds chirping", "generated_captions": "The audio contains the sounds of birds chirping and singing, as well as a man speaking."}
{"wav": "YAgaiowyYt88.wav", "ground_truth_captions": "A loud bang followed by silence", "generated_captions": "The audio contains the sound of an arrow being shot and hitting its target, along with background noise throughout."}
{"wav": "YTdl9SmBbRnA.wav", "ground_truth_captions": "A man is talking as a motor vehicle engine travels", "generated_captions": "The audio contains sounds of waves, surf, and wind."}
{"wav": "Y6OlHuvJR_Dk.wav", "ground_truth_captions": "Helicoptor flying", "generated_captions": "The audio contains the sound of an engine idling and revving, specifically a medium frequency engine."}
{"wav": "YbygBWUkpaC8.wav", "ground_truth_captions": "A man speaking with light wind followed by brief silence then birds chirping.", "generated_captions": "There is wind blowing, birds chirping and tweeting, and a man speaking."}
{"wav": "YFfUqv0Vv3ME.wav", "ground_truth_captions": "A horse walks while an adult male speaks, an adult female speaks briefly, and roosters are crowing in the distance", "generated_captions": "The audio contains wind noise, horse trotting sounds, and female speech."}
{"wav": "Ypgq2KPX5_SA.wav", "ground_truth_captions": "Some crinkling of cellophane", "generated_captions": "The audio contains the sound of paper crumpling and tearing, along with generic impact sounds."}
{"wav": "YH7rd9bZtbgc.wav", "ground_truth_captions": "Bells ringing repeatedly", "generated_captions": "The audio contains the sound of change ringing, also known as campanology, which is the art of ringing a set of tuned bells in a controlled manner."}
{"wav": "YO90Qy2xG6oA.wav", "ground_truth_captions": "Crying and screaming with some coughing", "generated_captions": "There is a baby crying and screaming, a woman laughing, and breathing sounds throughout the audio."}
{"wav": "YGuizRlAQ8qQ.wav", "ground_truth_captions": "High powered vibrations from a power tool", "generated_captions": "There is the sound of a power tool drilling throughout the entire duration of the audio, and there's also the sound of wood being sawed from 9.81 to 10 seconds."}
{"wav": "YoOMtaqvQ3_M.wav", "ground_truth_captions": "A helicopter flying with wind heavily blowing into a microphone", "generated_captions": "The audio contains the sound of an aircraft engine idling, which is described as 'propeller plane'."}
{"wav": "Y2ymiXjImwGs.wav", "ground_truth_captions": "Emergency vehicle driving with siren on", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a police car siren, and generic impact sounds."}
{"wav": "YWmDe2xbnSY4.wav", "ground_truth_captions": "Gunshots and explosions", "generated_captions": "The audio contains the sounds of gunfire, machine gun fire, and artillery fire."}
{"wav": "Y-DmjkgWa-rw.wav", "ground_truth_captions": "A bell ringing repeatedly", "generated_captions": "The audio contains the sound of church bells ringing."}
{"wav": "YKtinboYbmHQ.wav", "ground_truth_captions": "Tires squeal and an engine hums as a vehicle approaches", "generated_captions": "The audio contains the sound of a car accelerating and tires squealing, which is often associated with high-speed driving or racing."}
{"wav": "YrUq4w4EUSWA.wav", "ground_truth_captions": "An electronic motor buzzing and paper tearing followed by a bell chiming and a plastic click then a toilet flushing as paper crinkles in the background", "generated_captions": "The audio contains the sound of steam hissing and a train horn blowing."}
{"wav": "YHUwXtfYRFwk.wav", "ground_truth_captions": "A bus is traveling on the road", "generated_captions": "The audio contains the sound of an engine accelerating and then idling, which is characteristic of a large motor vehicle such as a truck or bus."}
{"wav": "Y0rSETXszQM0.wav", "ground_truth_captions": "Plastic clacking followed by a motorbike and a motorcycle engine starting up then accelerating", "generated_captions": "There is the sound of an engine starting and idling, along with generic impact sounds throughout the audio."}
{"wav": "YfwhkCnOeyC0.wav", "ground_truth_captions": "A man and a woman talking followed by a bell ringing and a cat meowing as a crowd of people applaud", "generated_captions": "The audio contains sounds of children shouting, talking, and playing, as well as background noise from an air conditioner."}
{"wav": "YEbpOXac13yo.wav", "ground_truth_captions": "Loud bus roaring and voices", "generated_captions": "The audio contains sounds of a subway train, mechanisms, and generic impact sounds."}
{"wav": "Y_YS5uKWoB6g.wav", "ground_truth_captions": "A baby cries as adults speak with clicking and banging of a car door", "generated_captions": "There is crying, babbling, and speech sounds throughout the audio clip from 0 to 10 seconds."}
{"wav": "YyhDw7PZje3g.wav", "ground_truth_captions": "Many insects are buzzing, and an adult male speaks", "generated_captions": "The audio contains sounds of insects buzzing, birds chirping and tweeting, and wind blowing into the microphone."}
{"wav": "Yjlwe9jtu5Gw.wav", "ground_truth_captions": "A couple of whistling sounds one after another", "generated_captions": "The audio contains whistling sounds throughout its duration, starting from the very beginning and lasting until almost ten seconds into the recording."}
{"wav": "Y4KObP7cREWw.wav", "ground_truth_captions": "Engine running and revving", "generated_captions": "The audio contains the sound of an engine accelerating and revving, idling, and medium frequency sounds throughout."}
{"wav": "Y35b9BSmN5JM.wav", "ground_truth_captions": "A wooden thud as an idle car engine runs then accelerates", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with generic impact sounds."}
{"wav": "YSGaIvgwwWSE.wav", "ground_truth_captions": "Rain and thunder", "generated_captions": "The audio contains the sounds of rain falling and thunder roaring."}
{"wav": "Y11SEBDuoqSk.wav", "ground_truth_captions": "An engine chugging loudly together with gunfire", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with machine gun fire."}
{"wav": "Yjid4t-FzUn0.wav", "ground_truth_captions": "A man speaks followed by a goat bleat", "generated_captions": "The audio contains sounds of mechanisms, wind, birds chirping and singing, water splashing, and a man speaking."}
{"wav": "Y4Ujigme2IxY.wav", "ground_truth_captions": "An engine humming and brakes squealing", "generated_captions": "The audio contains the sound of an engine accelerating and then idling, along with generic impact sounds."}
{"wav": "Ybpv_LneHmfU.wav", "ground_truth_captions": "An engine running", "generated_captions": "There is the sound of an engine idling throughout the duration of the audio, and there's also the sound of mechanisms."}
{"wav": "Y0Rpjl1AO-P0.wav", "ground_truth_captions": "A car engine idling then starts to rev shortly after", "generated_captions": "The audio contains the sound of an engine idling, which is a medium frequency engine noise."}
{"wav": "YFKaJsvcyHTk.wav", "ground_truth_captions": "A baby grunts and begins crying", "generated_captions": "There is crying, breathing sounds, and mechanisms throughout the entire duration of the audio."}
{"wav": "YJon_DEFqsfM.wav", "ground_truth_captions": "Wind blowing with ducks quacking and birds chirping", "generated_captions": "The audio contains sounds of ducks quacking, wind blowing into the microphone, and water splashing."}
{"wav": "YxUWSHYoslPQ.wav", "ground_truth_captions": "A man is getting a glass and setting in down on a hard surface", "generated_captions": "The audio contains sounds of dishes, pots, and pans clanging, along with male speech."}
{"wav": "Yg5l3Bz6lWnc.wav", "ground_truth_captions": "Insects buzzing as wood lightly shuffles and birds chirp in the distance", "generated_captions": "The audio contains sounds of birds chirping, insects buzzing, and wind blowing into the microphone."}
{"wav": "YqWYncqPSy9A.wav", "ground_truth_captions": "A man talking as an insect buzzes followed by a woman laughing then a man talking", "generated_captions": "The audio contains sounds of insects, birds chirping, and human speech."}
{"wav": "YXIooZl1QdM4.wav", "ground_truth_captions": "A man burping followed by belching while wheezing", "generated_captions": "There is a loud burp and breathing sounds throughout the audio, with no background music or other sounds mentioned."}
{"wav": "Yu8bQf0SnCVI.wav", "ground_truth_captions": "Some light banging followed by water splashing", "generated_captions": "The audio contains the sound of water running from a faucet and splashing into a sink, along with background noise."}
{"wav": "YQARuiRtfy-k.wav", "ground_truth_captions": "A power tool drilling followed by someone blows air then a man talking as rock music plays in the background", "generated_captions": "There is a sound of a drill being used throughout the entire duration of the audio, and there is also speech occurring from 3.58 to 10 seconds."}
{"wav": "YbUTOsLXYyxg.wav", "ground_truth_captions": "Man speaking followed by group laughter", "generated_captions": "The audio contains sounds of male speech, laughter, and finger snapping."}
{"wav": "Y6eX6bJOFftA.wav", "ground_truth_captions": "Ducks quack and men speak with distant humming", "generated_captions": "The audio contains sounds of ducks quacking, water splashing and gurgling, and background noise throughout the entire duration."}
{"wav": "Y2ErfX6ZT5pM.wav", "ground_truth_captions": "A toilet flushing", "generated_captions": "There is the sound of water running from a faucet and gurgling down a drain, along with generic impact sounds throughout the duration of the audio."}
{"wav": "YFDwK7T1JO_0.wav", "ground_truth_captions": "A male voice and then drilling", "generated_captions": "There is the sound of a drill being used, and a man speaking."}
{"wav": "YXrJcmftCY04.wav", "ground_truth_captions": "A crowd of people applauding and cheering", "generated_captions": "The audio contains the sound of an audience applauding, which is categorized as human group actions and applause."}
{"wav": "Ya_Rjlu50TfA.wav", "ground_truth_captions": "A series of sharp, squeaky snoring noises", "generated_captions": "The audio contains sounds of mechanisms, ticking, and breathing."}
{"wav": "Y1DKLyH3FixM.wav", "ground_truth_captions": "Nature sounds with birds chirping", "generated_captions": "The audio contains bird vocalizations and wind noise throughout its duration."}
{"wav": "Y6NBPiArs2-w.wav", "ground_truth_captions": "Footsteps followed by rapid gunshots and people speaking", "generated_captions": "There is a machine gun firing, followed by the sound of a gunshot and then a man speaking."}
{"wav": "YuJzAf4PaExI.wav", "ground_truth_captions": "An engine idling consistently", "generated_captions": "There is the sound of an engine idling throughout the entire duration of the audio, and there's also the sound of a car accelerating at one point."}
{"wav": "YJQz40TkjymY.wav", "ground_truth_captions": "Typing on a keyboard is ongoing in a quiet environment", "generated_captions": "The audio contains the sound of typing on a keyboard and mechanisms."}
{"wav": "Ykdflh3akyH8.wav", "ground_truth_captions": "Several puppies yapping", "generated_captions": "There is a dog whimpering and barking, a woman laughing, and background noise throughout the entire duration of the audio."}
{"wav": "YlmPMhs-9IYE.wav", "ground_truth_captions": "A vehicle engine revving as a crowd of people talk and whistle in the background", "generated_captions": "The audio contains sounds of accelerating, revving, vroom, car, motor vehicle (road), and race car - auto racing."}
{"wav": "YhGWarNR6xmg.wav", "ground_truth_captions": "Repetitive loud hissing with some static", "generated_captions": "There is the sound of a machine motor running and hissing throughout the entire duration of the audio, along with generic impact sounds occurring from 9.75 to 10.0 seconds."}
{"wav": "YZsf2YvJfCKw.wav", "ground_truth_captions": "Water trickling followed by a toilet flushing then liquid draining through a pipe", "generated_captions": "The audio contains the sound of water running from a faucet and a toilet flushing."}
{"wav": "Ynq0BF9zGkzg.wav", "ground_truth_captions": "An animal cries, followed by a crash, then two people speak with one another", "generated_captions": "There is a dog whimpering and barking, a man speaking, and background noise throughout the audio."}
{"wav": "Yvigslb0kClE.wav", "ground_truth_captions": "Goats bleating and a man speaking", "generated_captions": "The audio contains sounds of sheep, goat bleating, laughter, and conversation between men."}
{"wav": "Y2t82STv2GR8.wav", "ground_truth_captions": "Several church bells ringing", "generated_captions": "The audio contains the sound of change ringing, which is a method of campanology where bells are rung in a series of mathematical patterns called 'changes'."}
{"wav": "YzoctgurhvHE.wav", "ground_truth_captions": "A man speaks with some clicking as wind blows and a distant motor hums", "generated_captions": "There is wind noise throughout the audio, and there are sounds of mechanisms and generic impact sounds."}
{"wav": "YRdC8cviN6Bs.wav", "ground_truth_captions": "Rain falling followed by fabric rustling and footsteps shuffling then a vehicle door opening and closing as plastic crinkles", "generated_captions": "The audio contains the sounds of rain falling and wind blowing."}
{"wav": "YB8rdur4aams.wav", "ground_truth_captions": "Rustling and shaking followed by a horn and gusts of wind", "generated_captions": "The audio contains wind noise, waves crashing, and the sound of an aircraft engine running."}
{"wav": "Y3wrdPAeqjVI.wav", "ground_truth_captions": "A man talking followed by a camera muffling and footsteps shuffling then wood lightly clanking", "generated_captions": "The audio contains speech, breathing sounds, and generic impact sounds."}
{"wav": "Y6cS0FsUM-cQ.wav", "ground_truth_captions": "An adult male speaks, a cat caterwauls and hisses angrily, and an adult female speaks", "generated_captions": "The audio contains sounds of dogs barking, cats meowing, and human speech."}
{"wav": "YOmmPaIAXN0s.wav", "ground_truth_captions": "A man speaking followed by a horse trotting", "generated_captions": "The audio contains sounds of birds, dogs barking, and a man speaking."}
{"wav": "YbmEF-c-M174.wav", "ground_truth_captions": "A duck quacking and a bird chirping followed by footsteps on a wooden surface then a man talking", "generated_captions": "There is a man speaking, ducks quacking, and wind blowing throughout the audio."}
{"wav": "Y59VP93Tzjmg.wav", "ground_truth_captions": "Distant honks of a train horn with leaves rustling", "generated_captions": "The audio contains the sound of a train horn blowing and a train passing by."}
{"wav": "Y3VHpLxtd498.wav", "ground_truth_captions": "Humming with coos of pigeons and brief distant speaking", "generated_captions": "There is the sound of birds cooing and flapping their wings throughout the audio, along with some generic impact sounds."}
{"wav": "YOTLtzk0W4zg.wav", "ground_truth_captions": "An engine running and a male speaks", "generated_captions": "The audio contains the sound of an engine idling and a man speaking."}
{"wav": "YRtenf2XSXRc.wav", "ground_truth_captions": "A vehicle engine running idle then revving several times before a car door slams shut", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with background noise."}
{"wav": "YD9GHUPGWsV0.wav", "ground_truth_captions": "An adult female and adult male speak in the foreground, slight clattering is occurring, and an animal bleats in the background", "generated_captions": "There is background noise throughout the audio, and there are sounds of dogs barking and people talking."}
{"wav": "YT32kii824pA.wav", "ground_truth_captions": "A male speech and metal clanging.", "generated_captions": "The audio contains sounds of mechanisms, generic impact sounds, and breathing."}
{"wav": "YJBWJQCS4SvA.wav", "ground_truth_captions": "Wind noise on microphone with waves splashing in the background", "generated_captions": "The audio contains wind noise, waves crashing, and water splashing sounds."}
{"wav": "Yjf4iyQPJSvk.wav", "ground_truth_captions": "Water flowing and trickling", "generated_captions": "There is the sound of water flowing from a faucet throughout the entire duration of the audio, and there's also background noise."}
{"wav": "Yjs4dr5JusdM.wav", "ground_truth_captions": "A woman and man talk on the phone", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "Y5eSRL3PRHzo.wav", "ground_truth_captions": "An audience clapping", "generated_captions": "The audio contains the sound of people clapping and cheering, which is categorized as applause."}
{"wav": "Y-EQByFLFqig.wav", "ground_truth_captions": "A man speaks as rain pitter-patters and thunder rumbles", "generated_captions": "The audio contains the sounds of rain falling and thunder roaring, along with a man speaking."}
{"wav": "YHVz-FJBf_iM.wav", "ground_truth_captions": "A toilet flushing", "generated_captions": "There is the sound of water running from a faucet throughout the entire clip, and there's also background noise."}
{"wav": "YBXxlqaDvdaA.wav", "ground_truth_captions": "Male speech and wind blowing hard over microphone", "generated_captions": "The audio contains wind noise, waves crashing, and water splashing sounds."}
{"wav": "Y1PvMtRIlZNI.wav", "ground_truth_captions": "Gurgling and splashing water", "generated_captions": "There is the sound of water running and splashing throughout the entire duration of the audio, along with some background noise."}
{"wav": "YPMMdAKZxI_I.wav", "ground_truth_captions": "Burping and laughing by girls with distant speaking of a television", "generated_captions": "There is a cough, laughter, and speech by both male and female speakers throughout the audio."}
{"wav": "Yj0KvrVE_Oww.wav", "ground_truth_captions": "A door shutting followed by two men talking then a horn honking and slapping on a wooden surface", "generated_captions": "There is a man speaking, a horn honking, and footsteps walking on hard ground throughout the audio."}
{"wav": "YhuMLK0oA3L8.wav", "ground_truth_captions": "A man talking then whistling as guitar music plays", "generated_captions": "The audio contains background noise, breathing sounds, and speech by a male speaker."}
{"wav": "YilspW7JRjAg.wav", "ground_truth_captions": "A motor vehicle engine is revving", "generated_captions": "The audio contains the sound of an engine accelerating and revving, specifically a medium frequency engine."}
{"wav": "YEvZ3jOMYWxk.wav", "ground_truth_captions": "A woman is speaking in a quiet environment", "generated_captions": "The audio contains speech and breathing sounds."}
{"wav": "YL_CNz9Vrtkw.wav", "ground_truth_captions": "A man speaks followed by a crowd applauding", "generated_captions": "The audio contains sounds of clapping, cheering, and shouting from an audience, as well as male speech."}
{"wav": "YBL8ksJ0sTXk.wav", "ground_truth_captions": "An engine is idling followed by a male speaking", "generated_captions": "The audio contains the sound of an engine idling and a man speaking."}
{"wav": "Y4xrL4TSgHwU.wav", "ground_truth_captions": "A vehicle engine stuttering while starting up then running idle", "generated_captions": "There is the sound of a sewing machine running throughout the entire clip, and there's also the sound of paper crumpling that occurs from 6.87 to 10.02 seconds into the recording."}
{"wav": "YITlqMkR5alY.wav", "ground_truth_captions": "Wind blows hard followed by screaming", "generated_captions": "The audio contains the sounds of wind blowing and waves crashing, which are characteristic of oceanic environments."}
{"wav": "YIvg_q4t-3w0.wav", "ground_truth_captions": "White noise followed by brief, muffled speech and rustling", "generated_captions": "There is a continuous static noise throughout the audio, and there's also a woman speaking from 9.85 to 10 seconds."}
{"wav": "YwNiYSYJXssA.wav", "ground_truth_captions": "People are speaking followed by crowd noise", "generated_captions": "The audio contains sounds of people talking, shouting, and laughing."}
{"wav": "YzBXoaQ1GVlc.wav", "ground_truth_captions": "Several children speaking and screaming with a woman speaking briefly", "generated_captions": "There is a child speaking and shouting, along with other children shouting."}
{"wav": "Yf2fSxfvmkZQ.wav", "ground_truth_captions": "A man talking as metal thumps followed by plastic rustling then a power tool drilling while a metal pot clangs against a hard surface", "generated_captions": "There is a continuous mechanism sound throughout the audio, and there's also speech by a male in English."}
{"wav": "YU90e2P9jy30.wav", "ground_truth_captions": "A man yelling in the background as several basketballs bounce and shoes squeak on a hardwood surface", "generated_captions": "The audio contains sounds of basketball bouncing, squeaking shoes, and cheering crowd."}
{"wav": "YzEM94PH29VQ.wav", "ground_truth_captions": "A baby crying and various speeches", "generated_captions": "The audio contains sounds of a baby crying and breathing, along with background noise."}
{"wav": "YMPLZUg89y5U.wav", "ground_truth_captions": "Men speak with humming of an engine and some rustling", "generated_captions": "There is the sound of water running, mechanisms, and male speech throughout the audio."}
{"wav": "YelztUCeNQvQ.wav", "ground_truth_captions": "A train horn honking followed by a subway train running on railroad tracks", "generated_captions": "The audio contains the sound of a train horn blowing and a train passing by."}
{"wav": "YAizmnCDlXos.wav", "ground_truth_captions": "A bell ticks with a thumping noise", "generated_captions": "The audio contains the sound of a bell ringing, specifically a church bell."}
{"wav": "YZBtgrP4vU_w.wav", "ground_truth_captions": "Food and oil sizzling", "generated_captions": "There is the sound of food sizzling and frying, along with generic impact sounds throughout the duration of the audio."}
{"wav": "Y3qrVku794u0.wav", "ground_truth_captions": "A man speaks followed by a beep and a child speaks", "generated_captions": "The audio contains speech, breathing sounds, and background noise."}
{"wav": "Yktc_tJxw8sc.wav", "ground_truth_captions": "Low scratching groaning", "generated_captions": "There is a cat purring and snoring throughout the audio, along with background noise of mechanisms."}
{"wav": "YdP5DbAzTl5M.wav", "ground_truth_captions": "A motorboat engine running and a man speaking", "generated_captions": "There is the sound of an engine idling and a man speaking throughout the audio."}
{"wav": "YLWng-4PDzPM.wav", "ground_truth_captions": "Rustling followed by whistling", "generated_captions": "The audio contains whistling sounds throughout its duration, from the very beginning to almost ten seconds later."}
{"wav": "YIvfaKPDWC00.wav", "ground_truth_captions": "A siren ringing with a vehicle speeding closer", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a police car siren, and background noise."}
{"wav": "Ycr0GiZr0TNY.wav", "ground_truth_captions": "Children laughing with intermittent hissing", "generated_captions": "There is a baby laughing and a woman laughing in the background throughout the entire duration of the audio."}
{"wav": "Y-nQHwrRLfc0.wav", "ground_truth_captions": "Engine running steadily", "generated_captions": "The audio contains the sound of an engine idling, which is a medium frequency engine running at idle speed."}
{"wav": "Y1e98HeU9Vrg.wav", "ground_truth_captions": "Waves crash on a beach while the wind blows", "generated_captions": "The audio contains the sound of waves and surf, along with wind blowing into a microphone."}
{"wav": "Y1slvoNgzBLE.wav", "ground_truth_captions": "An electronic signal followed by compressed air releasing then an electronic bell playing as a train runs on tracks in the background", "generated_captions": "The audio contains the sound of a small engine running, wind blowing into a microphone, and a bell ringing."}
{"wav": "YfrOqlk0Wm5Y.wav", "ground_truth_captions": "A man speaking with intermittent metal scraping.", "generated_captions": "The audio contains speech and breathing sounds."}
{"wav": "YJZloTOdIY_c.wav", "ground_truth_captions": "Horses neighing and snorting while trotting on grass", "generated_captions": "The audio contains wind noise, bird vocalizations, and generic impact sounds."}
{"wav": "YIJ6pm5Kns8A.wav", "ground_truth_captions": "Woman speaks, girl speaks, clapping, croaking noise interrupts, followed by laughter", "generated_captions": "There is speech, laughter, and child speech in the audio."}
{"wav": "Yh0M4RS8p_mo.wav", "ground_truth_captions": "A man laughs followed by a baby crying", "generated_captions": "There is a baby laughing and crying, along with some background noise throughout the entire duration of the audio."}
{"wav": "Yz4MeV9IGVo0.wav", "ground_truth_captions": "Humming from loud engines with men speaking over the radio", "generated_captions": "There is a sound of a vehicle engine running throughout the audio, and there are also sounds of male speech and conversation."}
{"wav": "Y63KW_EQ72yU.wav", "ground_truth_captions": "A loud explosion as gusts of wind blow", "generated_captions": "The audio contains wind noise, microphone wind noise, and the sound of an aircraft engine running."}
{"wav": "YJfaj4P3us9M.wav", "ground_truth_captions": "A phone dial tone playing followed by a plastic switch flipping", "generated_captions": "There is clicking and tapping sounds throughout the audio, along with background noise."}
{"wav": "Y-NrFeH-kBSM.wav", "ground_truth_captions": "Clicks of weapons being loaded followed by a gunshot and a clink then a man speaks", "generated_captions": "The audio contains the sounds of gunfire, cap gun firing, and mechanisms."}
{"wav": "YnlC4UI4hZ60.wav", "ground_truth_captions": "An engine being turned over", "generated_captions": "The audio contains the sound of an engine accelerating and tires squealing, which is categorized as vehicle sounds."}
{"wav": "YE3D_z0aoUEg.wav", "ground_truth_captions": "A croaking frog with brief bird chirps", "generated_captions": "The audio contains the sounds of frogs croaking and insects buzzing."}
{"wav": "YE3Q1jfTeuWs.wav", "ground_truth_captions": "A baby cries followed by rustling and heavy breathing", "generated_captions": "There is a baby crying and babbling throughout the entire duration of the audio, from 0 to 10 seconds."}
{"wav": "YwoadpeAGHUQ.wav", "ground_truth_captions": "An emergency siren blaring steadily", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a police car siren, and background noise."}
{"wav": "YxIztYnMIWUA.wav", "ground_truth_captions": "An old fashioned telephone ring occurs repeatedly, and buzzing is present in the background", "generated_captions": "There is an alarm clock ringing throughout the entire duration of the audio, and there's also background noise present from 9.85 to 10 seconds."}
{"wav": "Y3ghVB-KaU_E.wav", "ground_truth_captions": "A man is speaking with hissing background noises", "generated_captions": "There is a continuous mechanism sound throughout the entire duration of the audio, and there is also speech by a male in English."}
{"wav": "Y2ItTq2JShdU.wav", "ground_truth_captions": "A train engine running", "generated_captions": "The audio contains the sound of a train running on railroad tracks and wind blowing into a microphone."}
{"wav": "YawxrHOpt-sE.wav", "ground_truth_captions": "A crowd of people talking and laughing with a motorbike engine running followed by a goat screaming then a person clicking", "generated_captions": "There is a goat bleating, people talking and laughing, and background noise throughout the entire duration of the audio."}
{"wav": "Yy3-M1sonh3M.wav", "ground_truth_captions": "Clinking followed by a toilet flushing", "generated_captions": "There is the sound of water running, followed by a toilet flushing and then more water running."}
{"wav": "Yir1XTdyt4IY.wav", "ground_truth_captions": "Released air hissing followed by a popping explosion then a metal ding persists as a person is laughing and a man is talking.", "generated_captions": "The audio contains video game sounds, explosions, and human voices."}
{"wav": "YWU3qB7gf6ao.wav", "ground_truth_captions": "An electronic beep and several faints ticks", "generated_captions": "There is the sound of mechanisms and ticking throughout, with brief periods of silence."}
{"wav": "YD1Sy7kRoaR8.wav", "ground_truth_captions": "A woman speaks via a public address system", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YWq4OD3olO2w.wav", "ground_truth_captions": "A man talks followed by laughter, and a woman and children communicate", "generated_captions": "There is a child speaking, children playing, and laughter throughout the audio."}
{"wav": "YARFFw0e_jig.wav", "ground_truth_captions": "A loud distorted belch followed by a series of burping", "generated_captions": "There is a loud burp and a ticking noise throughout the audio."}
{"wav": "Y3RultJjvTWI.wav", "ground_truth_captions": "'A group of young adults laughing followed by a man shouting as a stream of water splashes and flows while wind blows", "generated_captions": "There is speech, laughter, and water splashing sounds throughout the audio."}
{"wav": "YfK4QBQZ6i7w.wav", "ground_truth_captions": "People are laughing and chuckling", "generated_captions": "There is laughter, speech, and breathing sounds throughout the audio."}
{"wav": "YA61Mry8zBwE.wav", "ground_truth_captions": "Applause from a crowd with distant clicking and a man speaking over a loudspeaker", "generated_captions": "The audio contains sounds of clapping, cheering, and shouting from the crowd, as well as male speech."}
{"wav": "Y7-HCqJFwHoI.wav", "ground_truth_captions": "A person clicking on a keyboard", "generated_captions": "The audio contains the sound of typing on a computer keyboard, which is described as being loud and clear."}
{"wav": "Yd6gu2w19YQo.wav", "ground_truth_captions": "An baby laughing", "generated_captions": "There is a baby laughing and breathing sounds throughout the audio."}
{"wav": "YAagLJkfrFMk.wav", "ground_truth_captions": "Water hissing followed by a man breathing loudly then a toilet flushing", "generated_captions": "There is the sound of water running from a faucet and a toilet flushing."}
{"wav": "YA2mcp0N__7U.wav", "ground_truth_captions": "A crowd speak in the distance followed by sneezing", "generated_captions": "The audio contains sounds of mechanisms, laughter, and speech babble."}
{"wav": "YrjUrB1WUpcI.wav", "ground_truth_captions": "Water drains with gurgling noise", "generated_captions": "The audio contains the sound of water running from a faucet into a sink, and there is also background noise throughout the entire clip."}
{"wav": "Y9BukzlPNqC8.wav", "ground_truth_captions": "Soft drilling noise", "generated_captions": "There is the sound of a helicopter engine running throughout the entire clip from start to finish."}
{"wav": "Y8OTd45_6cvY.wav", "ground_truth_captions": "Footsteps running on a hard surface followed by liquid spraying then an animal growling as static plays in the background", "generated_captions": "There is a sound of water splashing and gurgling, accompanied by the sounds of pigs oinking and squealing."}
{"wav": "YPg2cWEnEEvc.wav", "ground_truth_captions": "Burping noises followed by tongue clapping sounds", "generated_captions": "There is burping, mechanisms, and surface contact sounds throughout the audio."}
{"wav": "YbIiiIo20PsY.wav", "ground_truth_captions": "A man speaking as insects are buzzing and wind is blowing into a microphone", "generated_captions": "The audio contains the sounds of insects, specifically bees and wasps, as well as a man speaking."}
{"wav": "YNDaVSIJaXVs.wav", "ground_truth_captions": "Aircraft engine and loud background roar", "generated_captions": "The audio contains the sound of an aircraft engine running at idle, specifically identified as a jet engine."}
{"wav": "Ygr5Zss89yLQ.wav", "ground_truth_captions": "A woman speaks, and a motor vehicle revs its engine", "generated_captions": "There is the sound of an engine accelerating and revving, as well as male speech throughout the audio."}
{"wav": "Y6ZFU4PqXmoI.wav", "ground_truth_captions": "A construction vehicle engine running and water splashing as wood crackles and snaps followed by electronic beeping and a man talking", "generated_captions": "The audio contains sounds of water splashing, waves crashing, and an engine running."}
{"wav": "Y3IScngdQA4I.wav", "ground_truth_captions": "A door shutting and a female speaking", "generated_captions": "The audio contains sounds of mechanisms, surface contact, and generic impact sounds."}
{"wav": "Y0fMXnvD38zI.wav", "ground_truth_captions": "Ocean waves crashing as water trickles as gusts of wind blow and seagulls squawk in the distance", "generated_captions": "The audio contains the sounds of waves, surf, wind noise from a microphone, and water splashing."}
{"wav": "YXZTt1xdK8uQ.wav", "ground_truth_captions": "An engine is accelerating", "generated_captions": "The audio contains the sound of an engine accelerating and revving, which is classified as a medium engine (mid frequency)."}
{"wav": "YWOywdRmySs0.wav", "ground_truth_captions": "A man talking followed by plastic crinkling and crumpling", "generated_captions": "The audio contains the sounds of paper crumpling and tearing, as well as male speech."}
{"wav": "YYk274Wr5iIE.wav", "ground_truth_captions": "Wind and water splashing and trickling", "generated_captions": "The audio contains the sound of water flowing and wind blowing into a microphone."}
{"wav": "YQ3vkJMVMbC8.wav", "ground_truth_captions": "A toilet flushes twice and a child speaks.", "generated_captions": "There is the sound of water running from a faucet, and a woman speaking."}
{"wav": "Yo_3MDLl_aH0.wav", "ground_truth_captions": "Loud explosions and burst that echo", "generated_captions": "The audio contains the sounds of explosions and artillery fire."}
{"wav": "YErxgH5g3Kx0.wav", "ground_truth_captions": "Hissing and buzzing of insects with a horse neigh and clip clops", "generated_captions": "The audio contains sounds of bees and wasps, wind blowing into the microphone, birds chirping, and rustling leaves."}
{"wav": "Ye4ph6bIC5zc.wav", "ground_truth_captions": "Distant murmuring and distant engine revving", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with the sound of wind blowing into a microphone."}
{"wav": "Ydkiwn2FdDVw.wav", "ground_truth_captions": "A woman speaks with distant quacks of a duck", "generated_captions": "The audio contains speech by a female speaker and background noise throughout the entire duration of the recording."}
{"wav": "Y4s2rRnu2PZo.wav", "ground_truth_captions": "Music plays continuously along with swooshing followed by a man speaking quickly", "generated_captions": "The audio contains music, video game sounds, and male speech."}
{"wav": "YAMQei29haCw.wav", "ground_truth_captions": "Buzzing and humming of a motor with a man speaking", "generated_captions": "The audio contains the sound of water flowing and splashing, as well as male speech."}
{"wav": "YAKHZMg9ba30.wav", "ground_truth_captions": "Clip-clop of horse while man speaks", "generated_captions": "The audio contains the sounds of clip-clopping, wind noise, and bird vocalizations."}
{"wav": "YTwR8BA6buMI.wav", "ground_truth_captions": "A piano playing as a clock ticks", "generated_captions": "The audio contains music and the sound of an ice cream truck playing its jingle."}
{"wav": "YLxu-3_h4kc4.wav", "ground_truth_captions": "Burping and then laughter", "generated_captions": "There is a loud burp followed by laughter and another burp."}
{"wav": "YOr7umk40TZA.wav", "ground_truth_captions": "An engine is idling with vibrating noises", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium engine (mid frequency)."}
{"wav": "YV4PLSw_WzVw.wav", "ground_truth_captions": "A vehicle engine revving as tires skid and squeal", "generated_captions": "The audio contains sounds of race car engines revving, tires squealing, and skidding."}
{"wav": "YjXkLS_QzUrI.wav", "ground_truth_captions": "A small motor is running, five hisses and a meow occur, then five more hisses and a meow occur", "generated_captions": "There is the sound of an electric shaver buzzing and vibrating, along with mechanisms and generic impact sounds throughout the duration of the audio."}
{"wav": "YAJtNitYMa1I.wav", "ground_truth_captions": "Food and oil sizzling", "generated_captions": "There is the sound of food frying and sizzling throughout the entire duration of the audio, along with some faint background noise."}
{"wav": "YR4fXcbWFhJg.wav", "ground_truth_captions": "Horses run in the distance then a man speaks and a woman cheers then talks", "generated_captions": "The audio contains sounds of people clapping, talking and running."}
{"wav": "YYflmW68gL4E.wav", "ground_truth_captions": "Burping and laughing from a young girl", "generated_captions": "There is a baby laughing, a woman speaking, and sounds of mechanisms throughout the audio."}
{"wav": "YxQDq3A4Zfbo.wav", "ground_truth_captions": "Water splashes and wind blows", "generated_captions": "The audio contains the sound of water running and splashing, along with wind noise picked up by the microphone."}
{"wav": "YinSvboaSRwA.wav", "ground_truth_captions": "A machine motor running as a man is speaking followed by rapid buzzing", "generated_captions": "The audio contains the sound of an electric toothbrush and mechanisms, as well as male speech."}
{"wav": "Yn74IYuCe_ms.wav", "ground_truth_captions": "A stream of water rushing and trickling followed by a young man whooshing", "generated_captions": "The audio contains the sound of water flowing, specifically from a waterfall or stream."}
{"wav": "YszkiW0GXEOI.wav", "ground_truth_captions": "Whistling with birds chirping", "generated_captions": "The audio contains whistling sounds throughout its duration, starting from the beginning and lasting until almost ten seconds into the recording."}
{"wav": "Y2RjqBRzmxaM.wav", "ground_truth_captions": "Music with rain falling and a woman speaking", "generated_captions": "The audio contains the sounds of rain falling and music playing, along with a woman speaking."}
{"wav": "YdmUOSyPXkUw.wav", "ground_truth_captions": "Compressed air and steam releasing with a man faintly talking in the background", "generated_captions": "There is the sound of a drill running throughout the entire clip, and there's also a man speaking from 6.37 to 8.45 seconds."}
{"wav": "YeUecAF626A8.wav", "ground_truth_captions": "Vehicles hum and vibrate as they rev their engines", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with the sound of water splashing."}
{"wav": "Yhmd6pa2e_rs.wav", "ground_truth_captions": "A bus engine is running, and people are talking", "generated_captions": "The audio contains sounds of motor vehicles, traffic noise, and roadway noise."}
{"wav": "YMTIF_l_8d4Q.wav", "ground_truth_captions": "A baby is crying and a child speaks in the background, then an adult female speaks and the baby sobs", "generated_captions": "There is a baby crying and babbling, along with some background noise throughout the entire duration of the audio."}
{"wav": "YMTaLknnq4wc.wav", "ground_truth_captions": "Whistling with some distant humming and a girl singing", "generated_captions": "The audio contains whistling sounds throughout its duration, starting from the beginning and lasting until almost ten seconds into the recording."}
{"wav": "Y2KR0C5ysO8o.wav", "ground_truth_captions": "An engine revving continuously", "generated_captions": "There is the sound of an engine accelerating and revving, along with medium frequency sounds throughout the duration of the audio."}
{"wav": "YKel-hfZ_9h8.wav", "ground_truth_captions": "Crunching and scraping followed by a child and a man speaking", "generated_captions": "There is crumpling and crinkling sounds, mechanisms, and surface contact sounds throughout the audio. There is also speech by both male and female speakers."}
{"wav": "YyVjivgsU2aA.wav", "ground_truth_captions": "An engine running followed by the engine revving and tires screeching", "generated_captions": "The audio contains the sound of a car accelerating and tires squealing, which is categorized as a vehicle sound."}
{"wav": "YfYTZVxQ8LJk.wav", "ground_truth_captions": "A woman is speaking, and a child speaks", "generated_captions": "The audio contains sounds of mechanisms, breathing, and child speech."}
{"wav": "YPuLuZ_TXv-0.wav", "ground_truth_captions": "Rapid typing and then sliding", "generated_captions": "The audio contains the sound of typing on a computer keyboard and mechanisms."}
{"wav": "Y3xDZ-kdGE3o.wav", "ground_truth_captions": "Metal clacking followed by a door closing as water trickles then a toilet flushing", "generated_captions": "There is the sound of water running and splashing, followed by a toilet flushing."}
{"wav": "YRfGapDlAYoQ.wav", "ground_truth_captions": "Musical whistling with wind blowing", "generated_captions": "The audio contains whistling sounds throughout its duration, from the very beginning to almost ten seconds later."}
{"wav": "YQKHpSAAjakY.wav", "ground_truth_captions": "A motorcycle engine is running, and a man is talking", "generated_captions": "The audio contains the sounds of an engine accelerating and revving, along with music playing in the background."}
{"wav": "Yi1u_2eZYYlE.wav", "ground_truth_captions": "An idle vehicle engine running", "generated_captions": "The audio contains the sound of an engine idling, specifically a lawn mower engine running at idle speed."}
{"wav": "YUE3XnVFodMI.wav", "ground_truth_captions": "Loud applause and woman speaking", "generated_captions": "The audio contains sounds of mechanisms, generic impact sounds, and surface contact, as well as male speech."}
{"wav": "Yy1a8PntuXYw.wav", "ground_truth_captions": "Mechanical humming followed by a flushing toilet", "generated_captions": "There is the sound of water filling up a toilet bowl and then flushing, along with generic impact sounds throughout the audio."}
{"wav": "YkgjNIDmO8a8.wav", "ground_truth_captions": "Emergency vehicle siren blasts while a man talks", "generated_captions": "There is an emergency vehicle siren and a car passing by in the background throughout the entire duration of the audio."}
{"wav": "Y473wBEwC35M.wav", "ground_truth_captions": "A man speaking as a vehicle horn honks and a man speaks in the distance", "generated_captions": "The audio contains sounds of mechanisms, wind noise from a microphone, and male singing with a truck horn honking in the background."}
{"wav": "YWHRnyGXcdy8.wav", "ground_truth_captions": "A baby crying loudly", "generated_captions": "There is a baby crying and sobbing throughout the entire duration of the audio, from 0:00 to 10:00 seconds."}
{"wav": "Y5ye0X5saadg.wav", "ground_truth_captions": "Helicopter running, speech on a radio, and then gunfire", "generated_captions": "The audio contains the sound of an aircraft engine idling and wind blowing into a microphone, along with male speech."}
{"wav": "Yr2djvq1vc68.wav", "ground_truth_captions": "A faucet pouring water as water fills a container followed by scrubbing on a plastic surface and water splashing", "generated_captions": "There is the sound of water running from a faucet and trickling into a sink, along with mechanisms sounds throughout the entire duration of the recording."}
{"wav": "YL8dA-2Lu2hY.wav", "ground_truth_captions": "A person whistling", "generated_captions": "The audio contains whistling sounds throughout its duration, and there is background noise of an unknown source."}
{"wav": "YsTMKled6Q1M.wav", "ground_truth_captions": "Whistling with pigeons cooing, wings flapping, and birds chirping", "generated_captions": "The audio contains sounds of birds chirping and cooing, as well as the flapping of wings."}
{"wav": "YvEWmHtiznF8.wav", "ground_truth_captions": "An engine running and a male speech", "generated_captions": "There is an engine idling throughout the audio, and there's also speech from both male and female speakers."}
{"wav": "Ytpm5IOD5d4o.wav", "ground_truth_captions": "An adult female speaks and claps, a bird whistles in the foreground, another bird chirps in the background, and then a human whistles a tune", "generated_captions": "There is a woman speaking, a dog whimpering and whining, and background noise throughout the audio."}
{"wav": "Y9xoYx3lTJ9I.wav", "ground_truth_captions": "Wind noise while a water vehicle is traveling across water, and a man talks", "generated_captions": "The audio contains the sounds of wind blowing and waves crashing, along with male speech."}
{"wav": "YzFzPOsOKog4.wav", "ground_truth_captions": "Rustling, bees buzzing and then birds chirping", "generated_captions": "The audio contains sounds of birds chirping, insects buzzing, and bees buzzing."}
{"wav": "YtaYKM1OSTwE.wav", "ground_truth_captions": "Sheep baaing as gusts of wind blows followed by a person chuckling", "generated_captions": "The audio contains sounds of ducks quacking, wind blowing into the microphone, and water splashing."}
{"wav": "Y5iTRKJqUIw8.wav", "ground_truth_captions": "Muffled crowd noise while a bell dings", "generated_captions": "The audio contains the sounds of a large crowd, bells ringing, and a clock ticking."}
{"wav": "YrvDcg9DoNKA.wav", "ground_truth_captions": "Distant thunder with rain falling followed by a man speaking loudly", "generated_captions": "The audio contains the sounds of rain falling and thunder clapping."}
{"wav": "YnU-AI3Cmc3M.wav", "ground_truth_captions": "A pigeon cooing followed by bird wings flapping as wind blows into a microphone", "generated_captions": "The audio contains sounds of birds cooing and flapping their wings, as well as generic impact sounds."}
{"wav": "Y_GI7meqlYZk.wav", "ground_truth_captions": "A cat screaming then meowing as a young boy is talking during a series of electronic buzzing", "generated_captions": "There is a baby crying and a woman speaking throughout the entire duration of the audio, from 0 to 10 seconds."}
{"wav": "Yh3UhoHIMfpw.wav", "ground_truth_captions": "Some rustling with a very high toned beep", "generated_captions": "There is a continuous background noise throughout the entire clip, and there's also a single beep heard at around 7 seconds into the recording."}
{"wav": "YLB6CZ0x-kns.wav", "ground_truth_captions": "A loud metal clank followed by pressurized air releasing as a truck engine runs idle before accelerating", "generated_captions": "The audio contains the sound of an aircraft engine running and accelerating, along with wind blowing into a microphone."}
{"wav": "YcFHFVGOtp6g.wav", "ground_truth_captions": "Gravely sound with women voice in background", "generated_captions": "The audio contains music, video game sounds, and the sound of something being crushed or broken."}
{"wav": "YCYUlLTKoa1Y.wav", "ground_truth_captions": "A woman speaks as a machine whirs and creaks in the background", "generated_captions": "There is the sound of frying food and dishes, pots, pans, and cutlery clattering throughout the audio."}
{"wav": "YP4qd8uodw_M.wav", "ground_truth_captions": "Muffled man speech with tapping and clicks", "generated_captions": "The audio contains speech, breathing sounds, and background noise."}
{"wav": "YMj_BO-iK1G4.wav", "ground_truth_captions": "Vibrations from a sewing machine with clicking", "generated_captions": "The audio contains the sound of a sewing machine running and rhythmic clacking, along with background noise."}
{"wav": "YptIksg9KEac.wav", "ground_truth_captions": "A person clapping followed by a dog barking then wood clanking as birds chirp and gusts of wind blow in the background", "generated_captions": "The audio contains sounds of dogs barking, birds chirping and singing, wind blowing into the microphone, and generic impact sounds."}
{"wav": "YCchRf2jq6fc.wav", "ground_truth_captions": "A young woman is talking.", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YFL8KTgMGrN4.wav", "ground_truth_captions": "A vacuum running", "generated_captions": "There is the sound of a helicopter engine running throughout the audio, and there's also the sound of wood being sawed from 10 seconds to almost 12 seconds into the recording."}
{"wav": "YqPYwp1K4sZE.wav", "ground_truth_captions": "A young girl speaking with some crinkling plastic", "generated_captions": "There is a child speaking, paper crumpling and crinkling sounds throughout the audio."}
{"wav": "Yo7-X8DAToGc.wav", "ground_truth_captions": "A vehicle driving by with tires briefly skidding and accelerating then slowing down", "generated_captions": "The audio contains the sound of a race car accelerating and skidding on tires."}
{"wav": "Y7XXSOzDQ2z0.wav", "ground_truth_captions": "A mid-size motor vehicle engine is idling and clacking somewhat, followed by mid-size motor vehicles accelerating quickly with a brief tire squeal", "generated_captions": "The audio contains sounds of a car accelerating and tires squealing, which is typical for a vehicle revving up and speeding off."}
{"wav": "YTtRtURWVYBE.wav", "ground_truth_captions": "Bells chiming as a clock is ticking", "generated_captions": "The audio contains the sound of change ringing, which is a method of ringing a set of tuned bells in a series of mathematical patterns called 'changes'."}
{"wav": "YPkmpxrsidZM.wav", "ground_truth_captions": "Applause and female speech and laughter, whistling, and then throat clearing", "generated_captions": "The audio contains sounds of clapping, cheering, and laughter from an audience."}
{"wav": "YlHh0SwUhP8U.wav", "ground_truth_captions": "Birds chirp followed by some clicking then gunshots", "generated_captions": "The audio contains bird vocalizations, wind noise, and generic impact sounds."}
{"wav": "YU3CAjsm1sec.wav", "ground_truth_captions": "Several cats meowing followed by a man singing", "generated_captions": "There is a cat meowing and caterwauling throughout the audio, along with generic impact sounds occurring at intervals from 1.54 to 2.09 seconds, and from 8.76 to 9.37 seconds."}
{"wav": "YdZDgJzGtLLU.wav", "ground_truth_captions": "Water splashing with some rustling and wind blowing", "generated_captions": "The audio contains the sounds of water flowing and wind blowing into a microphone."}
{"wav": "Y8b9z7N25DmU.wav", "ground_truth_captions": "A bus engine driving in the distance then nearby followed by compressed air releasing while a woman and a child talk in the distance", "generated_captions": "The audio contains sounds of traffic, motor vehicles (road), and an engine accelerating or revving up."}
{"wav": "YUQtBt6CQpwg.wav", "ground_truth_captions": "A man speaks, and a sewing machine sews material", "generated_captions": "There is a sound of a sewing machine running throughout the entire duration of the audio, and there's also speech by a male speaker."}
{"wav": "YhV4bDCBDCy0.wav", "ground_truth_captions": "Humming of a large truck engine with blowing wind", "generated_captions": "The audio contains the sound of an engine idling, which is a medium frequency sound."}
{"wav": "Y6TO9PEGpZcQ.wav", "ground_truth_captions": "An emergency siren wailing followed by a large truck engine running idle", "generated_captions": "There is an emergency vehicle siren and traffic noise throughout the audio clip."}
{"wav": "YbAqgL5dCQOE.wav", "ground_truth_captions": "Rain falling with distant hums of traffic", "generated_captions": "The audio contains the sound of rain falling on a surface and wind blowing into a microphone."}
{"wav": "YbJMMp6PLKqM.wav", "ground_truth_captions": "A baby cries and a young child speaks", "generated_captions": "There is babbling, crying, and breathing sounds throughout the audio."}
{"wav": "YNeZerAPXR-A.wav", "ground_truth_captions": "Woman laughing and talking with another man and woman while something is clanging", "generated_captions": "There is laughter, speech, and breathing sounds throughout the audio."}
{"wav": "Y6cyKp3EDm-0.wav", "ground_truth_captions": "Pigeons are cooing flapping and a man talks", "generated_captions": "The audio contains the sounds of birds cooing and flapping their wings, as well as generic impact sounds."}
{"wav": "Y1N_DtRpdAp8.wav", "ground_truth_captions": "A mid-size engine is idling and vibrating and is revved up one time", "generated_captions": "The audio contains the sound of an engine idling, which is described as medium frequency and lasts for 10 seconds from the start of the recording."}
{"wav": "Yv7BaYF0kagM.wav", "ground_truth_captions": "An engine running", "generated_captions": "There is the sound of an engine idling throughout the entire clip, and there's also the sound of a power tool being used."}
{"wav": "YrN2rpLV3brs.wav", "ground_truth_captions": "Dishes clanking as a man is talking", "generated_captions": "The audio contains sounds of dishes, pots, and pans clanging, mechanisms, and male speech."}
{"wav": "Yt1hj7se76wQ.wav", "ground_truth_captions": "Typing on a typewriter is ongoing with clicking and clacking, a bell rings, and a clack occurs with the carriage return", "generated_captions": "The audio contains the sound of typing on a typewriter throughout its duration, from start to finish."}
{"wav": "Y8BPTQO_cx7E.wav", "ground_truth_captions": "A man speaking followed by applause and laughter from an audience", "generated_captions": "The audio contains sounds of applause, cheering, and whistling from the crowd, as well as male speech."}
{"wav": "Y3n05BjV7r7M.wav", "ground_truth_captions": "A series of metal clanks and rattling as a small motor operates and hums", "generated_captions": "The audio contains the sound of a sewing machine running, specifically a medium frequency engine knocking and mechanisms sounds."}
{"wav": "YB-gTt3_rceQ.wav", "ground_truth_captions": "Small child with a man and woman speaking", "generated_captions": "The audio contains sounds of children speaking, crying, and laughing, as well as generic impact sounds."}
{"wav": "Y8DLcBdC5UrE.wav", "ground_truth_captions": "Wind followed by splashing of water", "generated_captions": "The audio contains the sounds of wind blowing and waves crashing, along with generic impact sounds."}
{"wav": "Y_C2HinL8VlM.wav", "ground_truth_captions": "Metal clanking and hammering in the distance followed by police sirens sounding", "generated_captions": "The audio contains the sounds of mechanisms, generic impact sounds, and glass shattering."}
{"wav": "YAWGnTI0e2Fs.wav", "ground_truth_captions": "Helicopter propellers spinning", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "YrPkCYq4Zjwk.wav", "ground_truth_captions": "A whoosh effect followed by a woman talking then a man talking proceeded by another man talking over a radio as guitar music plays in the background", "generated_captions": "The audio contains video game sounds, explosions, and gunfire."}
{"wav": "YCfxWJ1Qoufg.wav", "ground_truth_captions": "A man talking as paper crinkles followed by plastic creaking then a toilet flushing", "generated_captions": "There is the sound of water running, a toilet flushing, and male speech throughout the duration of the audio."}
{"wav": "YBA-lFjpzad4.wav", "ground_truth_captions": "Motor vehicle traffic is ongoing, and a motorcycle engine accelerates and then decelerates in the foreground", "generated_captions": "The audio contains the sound of an engine revving and accelerating, as well as generic impact sounds."}
{"wav": "YC8kR19NvynA.wav", "ground_truth_captions": "A man speaking continuously", "generated_captions": "The audio contains speech by a male speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YtIM-H2rdq8U.wav", "ground_truth_captions": "A gun firing several times followed by a revolver chamber spinning and metal clanking as a man talks and a person grunts", "generated_captions": "The audio contains machine gun fire, background noise, and male speech."}
{"wav": "YBvw2gv1fcZw.wav", "ground_truth_captions": "A person speaks followed by a burping sound and laughter", "generated_captions": "There is a sound of someone burping and laughing, as well as a sound effect of a fart."}
{"wav": "YlYhwCRX2wNc.wav", "ground_truth_captions": "A woman talking as water trickles followed by porcelain dishes clanking", "generated_captions": "The audio contains the sounds of frying food and dishes, pots, and pans clanging."}
{"wav": "YMdlEswBfZMQ.wav", "ground_truth_captions": "One toddler crying with several others laughing", "generated_captions": "There is a baby crying and babbling throughout the entire duration of the audio, from 0 to 10 seconds."}
{"wav": "YMBP4RcnwGZw.wav", "ground_truth_captions": "A woman talking then laughing as a crowd of people talk in the background", "generated_captions": "There is speech noise, laughter, and conversation sounds throughout the audio."}
{"wav": "YpPLisQ_QXxw.wav", "ground_truth_captions": "An engine running and a horn", "generated_captions": "The audio contains sounds of vehicles, horns honking, and traffic noise."}
{"wav": "Y4_DjmCg8Ra8.wav", "ground_truth_captions": "Artillery guns fire followed by a man yelling as someone whistles while gunshots fire and a group of men shout in the background", "generated_captions": "The audio contains video game sounds, music, and gunshots."}
{"wav": "YNX0gR9Eebp0.wav", "ground_truth_captions": "A child speaking as water trickles and splashes followed by a woman moaning", "generated_captions": "There is a child speaking, water splashing and gurgling sounds throughout the audio."}
{"wav": "Yb1PXsfgQw5w.wav", "ground_truth_captions": "A group of people laughing followed by a man talking then more laughter", "generated_captions": "There is laughter, speech, and breathing sounds throughout the audio."}
{"wav": "YN_s9F4CI_98.wav", "ground_truth_captions": "Pigeons cooing followed by bird wings flapping", "generated_captions": "The audio contains sounds of birds cooing and flapping their wings, along with generic impact sounds."}
{"wav": "YWqXFAY4k79s.wav", "ground_truth_captions": "Several loud pops followed by one woman laughing and another speaking", "generated_captions": "There is speech, laughter, and generic impact sounds throughout the audio."}
{"wav": "Y13CBvjHZhOA.wav", "ground_truth_captions": "Knocking sounds as race cars pass by", "generated_captions": "The audio contains sounds of motor vehicles, traffic passing by, and people talking."}
{"wav": "YXPebkNzsnRI.wav", "ground_truth_captions": "Whistling followed by a child giggling and then Moe whistling", "generated_captions": "The audio contains whistling sounds, breathing and human sounds."}
{"wav": "Ye9MWXS34o48.wav", "ground_truth_captions": "A person breathes heavily and sneezes", "generated_captions": "There is breathing, sighing, and snorting sounds throughout the audio clip from 0 to 10 seconds."}
{"wav": "YNi3dIj90Oa4.wav", "ground_truth_captions": "Explosion followed by man speaking a short bit of music at the end", "generated_captions": "The audio contains video game sounds, explosions, and gunfire."}
{"wav": "YPYP-r0nvbFk.wav", "ground_truth_captions": "Wind blows and a man speaks followed by a goat bleating", "generated_captions": "The audio contains sounds of ducks quacking, wind blowing into the microphone, and birds chirping."}
{"wav": "YCxaPpRJRkn0.wav", "ground_truth_captions": "Male snoring loudly", "generated_captions": "There is snoring and breathing sounds throughout the audio, with background noise of mechanisms."}
{"wav": "YgwQMkQmBITE.wav", "ground_truth_captions": "A man talking followed by several lights scrapping on a wooden surface as wood clanks in the background", "generated_captions": "The audio contains the sounds of paper rustling, crumpling and tearing, as well as male speech."}
{"wav": "YwrQDkX0NbTA.wav", "ground_truth_captions": "A distant engine hums loudly with splashing water and blowing wind", "generated_captions": "The audio contains the sounds of waves, surf, and wind blowing into a microphone."}
{"wav": "YC_ga5m6nOhI.wav", "ground_truth_captions": "A train running on train tracks while a steam engine horn whistles", "generated_captions": "The audio contains the sound of a train horn blowing and a train passing by."}
{"wav": "Y3kBlVLkN0zo.wav", "ground_truth_captions": "Wind is blowing and birds are chirping, a metal bell clangs quietly once, and multiple animals bleat while two men speak in the background", "generated_captions": "The audio contains sounds of birds, insects, wind, and a cowbell ringing."}
{"wav": "YGkb4f6yodPE.wav", "ground_truth_captions": "Sustained industrial sawing noise", "generated_captions": "There is the sound of a power tool drilling into wood throughout the entire duration of the audio, and there's also the sound of mechanisms operating from 10 seconds to almost the end of the clip at approximately 9.82 seconds."}
{"wav": "YtxeXrpoMST4.wav", "ground_truth_captions": "Water turning on and running continuously", "generated_captions": "There is the sound of water running from a faucet throughout the entire clip, and there's also background noise."}
{"wav": "YQOmV7O9mFwg.wav", "ground_truth_captions": "Laughing followed by a child talking and more laughing with many children talking in the background", "generated_captions": "There is a child speaking and laughing, as well as sounds of mechanisms and dishes, pots, and pans clattering."}
{"wav": "YZsTZ7jqbd9M.wav", "ground_truth_captions": "A man talking during footsteps on leaves as birds chirp in the background.", "generated_captions": "The audio contains sounds of birds chirping, wind blowing into the microphone, and generic impact sounds."}
{"wav": "YPVvi2SDOjVc.wav", "ground_truth_captions": "A vehicle is running followed by the horn honking", "generated_captions": "The audio contains the sound of an aircraft engine running and wind blowing into a microphone."}
{"wav": "YkVYNXZd0MMY.wav", "ground_truth_captions": "An idle vehicle engine running followed by bird cawing in the background and a plastic camera click", "generated_captions": "The audio contains the sound of an engine idling and then revving up, which is characteristic of a car or truck engine."}
{"wav": "YK2kIOBeCfuo.wav", "ground_truth_captions": "An adult male speaks, and a crowd laughs and then cheers and applauds", "generated_captions": "The audio contains sounds of clapping, cheering, and laughter from the crowd."}
{"wav": "Yos_2U4xqTqw.wav", "ground_truth_captions": "Heavy footsteps walking on a hard surface followed by a man grunting then two explosions", "generated_captions": "There is wind blowing, rustling leaves, and footsteps on gravel."}
{"wav": "YeNG6fEiAE8c.wav", "ground_truth_captions": "Men laughing with goat bleating in background", "generated_captions": "There is laughter, speech, and the sound of water splashing."}
{"wav": "YMjSegUnQXr4.wav", "ground_truth_captions": "Pigeons cooing and bird wings flapping during light scrapping on a metal surface while a construction machine operates in the background", "generated_captions": "The audio contains the sounds of birds cooing and flapping their wings, as well as generic impact sounds."}
{"wav": "YC5kmOK_l4jc.wav", "ground_truth_captions": "A young girl talking as an infant is laughing", "generated_captions": "There is a baby laughing and babbling, a woman speaking, and some background noise throughout the audio."}
{"wav": "Yq4YFJA5pFXc.wav", "ground_truth_captions": "A helicopter engine whines as it starts", "generated_captions": "There is the sound of an aircraft engine running throughout the audio, and there's also the sound of wood being sawed from 9.25 to 10.00 seconds."}
{"wav": "YSNIaYhri76w.wav", "ground_truth_captions": "A pig squeals and dogs bark followed by a man speaking", "generated_captions": "The audio contains sounds of dogs barking, growling and whining, as well as the sound of glass clinking."}
{"wav": "Y1OyEgzXCkYE.wav", "ground_truth_captions": "A male speaking over a microphone", "generated_captions": "The audio contains speech and breathing sounds."}
{"wav": "Y86dNVnTwH6U.wav", "ground_truth_captions": "Hissing followed by sewing machine running", "generated_captions": "The audio contains the sound of an engine running and water splashing, which could be from a vehicle or machinery."}
{"wav": "Y-aYumc8KoXg.wav", "ground_truth_captions": "A vehicle is driving, and a horn is honking", "generated_captions": "The audio contains the sound of a motorboat speeding through water and wind blowing into a microphone."}
{"wav": "YhxbmDeNSO6Q.wav", "ground_truth_captions": "A sewing machine sews followed by a man talking", "generated_captions": "There is a man speaking, followed by the sound of a sewing machine running."}
{"wav": "YJp64Whpr3BA.wav", "ground_truth_captions": "Rustling followed by a sewing machine running.", "generated_captions": "The audio contains the sounds of mechanisms, sewing machines, and ticks."}
{"wav": "Y3fomsZXG3aM.wav", "ground_truth_captions": "A vehicle engine running idle then revving after two metal clicks", "generated_captions": "The audio contains the sound of an engine idling and then revving up, which is characteristic of a car engine."}
{"wav": "YrtgVoZCcBw8.wav", "ground_truth_captions": "Goats are bleating with other natural outdoor noises", "generated_captions": "There is a goat bleating, birds chirping and tweeting, and background noise throughout the entire duration of the audio."}
{"wav": "YVOXl8iR-HnI.wav", "ground_truth_captions": "Quiet speech and then and airplane flying away", "generated_captions": "There is an aircraft engine running and wind blowing into the microphone throughout the audio."}
{"wav": "Y4pf-PIymDhU.wav", "ground_truth_captions": "A jackhammer drilling and vibrating continuously", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "YsJrFyjfrL-g.wav", "ground_truth_captions": "A sewing machine operating during several metal clacks", "generated_captions": "The audio contains the sound of typing on a typewriter, specifically the clacking noise made by the keys hitting the paper as they are pressed down."}
{"wav": "YCvNAwby6Xos.wav", "ground_truth_captions": "A sewing machine operating several times followed by gears cranking as a man is talking", "generated_captions": "There is the sound of a sewing machine running and intermittent clicking, as well as generic impact sounds throughout the audio."}
{"wav": "Y4_Cak7gvly4.wav", "ground_truth_captions": "Percussion music playing alongside a series of whooshes followed by a motor humming", "generated_captions": "The audio contains the sounds of gunfire, explosions, and music playing in the background."}
{"wav": "Y1j5NMuq1X30.wav", "ground_truth_captions": "High pressure liquid spraying as a radio plays in the background", "generated_captions": "There is the sound of steam hissing throughout the entire duration of the audio, and there's also the sound of water splashing from 9:78 to 10:00."}
{"wav": "YdJYO3RbBabE.wav", "ground_truth_captions": "An electronic beep followed by a man talking", "generated_captions": "There is a beep, mechanisms sounds, and male speech throughout the audio."}
{"wav": "YIPfaRF76gVU.wav", "ground_truth_captions": "A truck engine driving by while emergency sirens wail as a crowd of people talk followed by a man speaking over an intercom", "generated_captions": "There is a crowd cheering and applauding, an emergency vehicle siren blaring, and a motor vehicle engine running throughout the audio."}
{"wav": "YriM7b5bJ9KQ.wav", "ground_truth_captions": "A man laughs followed by laughter and speech from other people", "generated_captions": "The audio contains sounds of laughter, speech babble, and male singing."}
{"wav": "YaMhu5eMQAsI.wav", "ground_truth_captions": "Humming from a large engine", "generated_captions": "There is the sound of an engine idling throughout the entire clip, and there's also the sound of water splashing."}
{"wav": "YHqnSyliKTKA.wav", "ground_truth_captions": "'An engine with people speaking and a horse neighing", "generated_captions": "The audio contains sounds of mechanisms, wind noise from the microphone, bird vocalizations, and human voices."}
{"wav": "YhpDltmawxIM.wav", "ground_truth_captions": "Water pouring from a faucet onto a metal surface and filling a glass container", "generated_captions": "There is the sound of water running from a faucet and splashing into a sink throughout the entire duration of the audio, along with background noise."}
{"wav": "Yazh_-OkQ-uI.wav", "ground_truth_captions": "A woman talks briefly as several goats bleat including one that has high pitched bleats. A crunch is followed by a man speaking", "generated_captions": "The audio contains sounds of mechanisms, generic impact sounds, and human voices including speech and babbling. There is also the sound of a duck quacking."}
{"wav": "Y0ury8KHQdL4.wav", "ground_truth_captions": "An adult male is speaking and typing on a keyboard", "generated_captions": "The audio contains speech by a male speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YBLMWD6fxhpo.wav", "ground_truth_captions": "A grunt from a person followed by footsteps and oinks from a pig with a single squeal", "generated_captions": "There is a pig oinking and squealing throughout the entire duration of the audio, along with some rustling sounds."}
{"wav": "YUV1kdjwpy6U.wav", "ground_truth_captions": "An engine vibrates followed by a man speaking", "generated_captions": "There is the sound of an engine idling and accelerating, as well as male speech throughout the audio."}
{"wav": "YIhvXtS9-IxM.wav", "ground_truth_captions": "A high pitched engine idling", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "Yrp3CQsWxVgE.wav", "ground_truth_captions": "White noise followed by a musical horn honking", "generated_captions": "The audio contains sounds of mechanisms, wind noise on microphone, and vehicle horn honking."}
{"wav": "Y1Uh74_rZ72k.wav", "ground_truth_captions": "Wind blowing with passing distant traffic and some rumbling", "generated_captions": "The audio contains sounds of an aircraft engine and wind blowing into the microphone."}
{"wav": "YKSHpYhuTotY.wav", "ground_truth_captions": "A man speaking as footsteps walk on grass while insects are buzzing", "generated_captions": "The audio contains sounds of insects, mechanisms, and ticks."}
{"wav": "YLCwSUVuTyvg.wav", "ground_truth_captions": "A series of doors sliding open as gusts of wind blows and glass clanks", "generated_captions": "The audio contains wind noise, generic impact sounds, and the sound of a horse trotting."}
{"wav": "YvruDH_YLaPI.wav", "ground_truth_captions": "Gunshots are ongoing, and intermittent metal clinks are occurring", "generated_captions": "The audio contains the sounds of machine gun fire, gunshots, and other noises."}
{"wav": "YlTfNLKEy1RU.wav", "ground_truth_captions": "Repetitive faint snoring", "generated_captions": "There is snoring and breathing sounds throughout the audio, with occasional impact sounds."}
{"wav": "YLVvS3s9dFKw.wav", "ground_truth_captions": "A man speaking while water runs in the background", "generated_captions": "There is the sound of water running throughout the entire duration of the audio, and there is also speech from 0 to 10 seconds."}
{"wav": "Y0_ogYGDGDco.wav", "ground_truth_captions": "Water is splashing, people are talking", "generated_captions": "The audio contains sounds of water splashing and gurgling, as well as male speech."}
{"wav": "Y2EsxcKe1A4w.wav", "ground_truth_captions": "A large dog barks", "generated_captions": "There is a dog barking and growling throughout the entire duration of the audio, with some background noise also present."}
{"wav": "Y5rh5-MCjqq8.wav", "ground_truth_captions": "A brief loud snoring", "generated_captions": "There is snoring and breathing sounds throughout the audio, with background noise of mechanisms."}
{"wav": "YDzKjogSVOLM.wav", "ground_truth_captions": "Ducks quacking and birds chirping followed by a rooster crowing as a crowd of people talk", "generated_captions": "The audio contains sounds of ducks, birds chirping and singing, rooster crowing, and wind blowing into the microphone."}
{"wav": "YGIOApFAWDOc.wav", "ground_truth_captions": "Birds chirping and tweeting followed by light wood tapping", "generated_captions": "The audio contains bird vocalizations and chirping sounds throughout its duration, along with the sound of water splashing at intervals from 9:58 to 10:02."}
{"wav": "Y5G6b_QWL3nY.wav", "ground_truth_captions": "A woman is speaking while food is frying and sizzling", "generated_captions": "The audio contains the sounds of frying food and sizzling, along with female speech."}
{"wav": "Y-oy0BkpMGAk.wav", "ground_truth_captions": "Revving of an engine and a skidding sound", "generated_captions": "The audio contains the sound of an engine revving and accelerating, specifically a medium frequency engine."}
{"wav": "Yoklu5ZJD_2U.wav", "ground_truth_captions": "Plastic tapping then rattling as a bird chirps", "generated_captions": "The audio contains the sounds of birds chirping and singing, as well as generic impact sounds."}
{"wav": "YinQOrxc_oZo.wav", "ground_truth_captions": "Hog snorting with male screaming", "generated_captions": "There is a pig oinking and breathing sounds throughout the audio, along with background noise."}
{"wav": "YECw5Yf7QoMo.wav", "ground_truth_captions": "A man speaks while another speaks on top as well followed by clapping", "generated_captions": "The audio contains sounds of speech, laughter, and shouting."}
{"wav": "Y4abZbau8tZo.wav", "ground_truth_captions": "Waves roll in and a man speaks", "generated_captions": "The audio contains sounds of waves, surf, and wind blowing into the microphone."}
{"wav": "YpuZL08fzpXk.wav", "ground_truth_captions": "Gunshots followed by people speaking and explosions", "generated_captions": "The audio contains video game sounds, gunfire, and explosions."}
{"wav": "Yx5AH2gW_8S4.wav", "ground_truth_captions": "Pigeons cooing with some rattling and screeching", "generated_captions": "The audio contains sounds of birds cooing and flapping their wings, as well as generic impact sounds."}
{"wav": "YpCQEWAFGEjc.wav", "ground_truth_captions": "A steam engine running on railroad tracks as steam releases and hisses while group of people talk in the background", "generated_captions": "There is the sound of a helicopter engine running throughout, and there's also a man speaking intermittently from 10.58 to 12.36 seconds."}
{"wav": "YZNEZLlDVgrE.wav", "ground_truth_captions": "Buzzing nearby insects with men speaking", "generated_captions": "There is a buzzing insect throughout the audio, and there's also a man speaking from 4.53 to 10.02 minutes into the recording."}
{"wav": "YGMP8m09j5vk.wav", "ground_truth_captions": "Birds call while another bird sings", "generated_captions": "The audio contains bird vocalizations and chirping sounds throughout its duration, with additional background noise from 10.0 to 10.0 seconds."}
{"wav": "Y4fz0-Kx2oNs.wav", "ground_truth_captions": "Food and oil sizzling followed by a person snapping", "generated_captions": "The audio contains the sound of food sizzling on a pan."}
{"wav": "YVZLZ08k3YeA.wav", "ground_truth_captions": "Someone snores and a man speaks", "generated_captions": "There is a continuous snoring sound throughout the entire duration of the audio, and there's also a brief moment where someone is speaking."}
{"wav": "YJTHMXLC9YRs.wav", "ground_truth_captions": "Breathing and ducks quaking", "generated_captions": "The audio contains sounds of ducks quacking, wind blowing into the microphone, and birds chirping."}
{"wav": "YnD1K1Zo0qrM.wav", "ground_truth_captions": "A series of machine gunfire and two gunshots firing as a jet aircraft flies by followed by soft music playing", "generated_captions": "There is a machine gun firing, a gunshot, and a duck quacking."}
{"wav": "YpWQeV08kYR0.wav", "ground_truth_captions": "An ambulance sounds the siren", "generated_captions": "There is an emergency vehicle siren and traffic noise throughout the audio clip."}
{"wav": "YhDMHIDJdfDA.wav", "ground_truth_captions": "Continuous snoring", "generated_captions": "There is snoring and breathing sounds throughout the audio, with background noise of mechanisms."}
{"wav": "YQv1HXaT-28U.wav", "ground_truth_captions": "Liquid spraying and splattering on a hard surface as kids laugh in the background", "generated_captions": "There is the sound of water running from a faucet and some rustling, as well as a woman speaking."}
{"wav": "YC4JwGJQ2dUA.wav", "ground_truth_captions": "A man yelling very loudly while speaking", "generated_captions": "There is speech, singing, and shouting throughout the audio."}
{"wav": "YfWvWhLJ5Fow.wav", "ground_truth_captions": "Running then spraying", "generated_captions": "There is the sound of something sizzling and hissing throughout the entire duration of the audio, along with intermittent generic impact sounds occurring at various intervals."}
{"wav": "YBzHTqyX69pI.wav", "ground_truth_captions": "Wood sawing and scrapping followed by a woman speaking while pigeons are cooing and bird wings are flapping", "generated_captions": "The audio contains the sounds of pigeons cooing and flapping their wings, as well as a child speaking."}
{"wav": "YljrL7Cb-jr8.wav", "ground_truth_captions": "Humming and vibrating of engines", "generated_captions": "The audio contains the sound of an engine idling and revving, specifically from a medium-sized vehicle or motorcycle."}
{"wav": "YrBUCIK8JRLg.wav", "ground_truth_captions": "White noise followed by some rustling and splashing", "generated_captions": "There is the sound of water running and splashing throughout the entire duration of the audio, along with some generic impact sounds occurring towards the end."}
{"wav": "YTSnq6n8tElo.wav", "ground_truth_captions": "A young child talking followed by tapping on glass then metal rattling on a glass surface", "generated_captions": "The audio contains sounds of mechanisms, generic impact sounds, and surface contact."}
{"wav": "YPO8Nu3F8mkA.wav", "ground_truth_captions": "Several pops and bursts of fireworks exploding", "generated_captions": "The audio contains the sounds of fireworks and firecrackers, specifically machine gun-like noises."}
{"wav": "YemGPabOePzA.wav", "ground_truth_captions": "Laughing and speech in a slowed speed", "generated_captions": "There is laughter and speech throughout the audio, with a male voice speaking English."}
{"wav": "YPTyFYxXdut4.wav", "ground_truth_captions": "A woman speaks as water splashes", "generated_captions": "There is the sound of frying food and female speech throughout the duration of the audio."}
{"wav": "Y_oKXrY5Ff0g.wav", "ground_truth_captions": "Speech and laughter from many people", "generated_captions": "There is speech, laughter, and breathing sounds throughout the audio."}
{"wav": "YKOBkbROPv4c.wav", "ground_truth_captions": "Humming of an engine with squealing tires", "generated_captions": "The audio contains sounds of race car engines revving and tires squealing, along with music playing in the background."}
{"wav": "Y32565FEuksc.wav", "ground_truth_captions": "A woman speaks and a crowd applauds", "generated_captions": "The audio contains sounds of clapping, cheering, and shouting from an audience."}
{"wav": "YI_vN_BFUr0Y.wav", "ground_truth_captions": "A train horn blowing several times as a train runs on railroad tracks and a railroad crossing signal rings in the distance", "generated_captions": "The audio contains the sound of a train horn blowing and wind blowing into a microphone."}
{"wav": "YwBs02amFGXs.wav", "ground_truth_captions": "A rooster crowing and birds cooing", "generated_captions": "The audio contains the sounds of chickens and roosters crowing, along with background noise."}
{"wav": "YwVi5w_NU6CM.wav", "ground_truth_captions": "A fire truck siren blasts", "generated_captions": "There is an emergency vehicle siren and wind noise throughout the audio."}
{"wav": "Y7WkB6pflr6o.wav", "ground_truth_captions": "A woman speaking", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YrE6BJ0Bo4w4.wav", "ground_truth_captions": "A woman speaks, and faucet water runs", "generated_captions": "There is the sound of water running from a faucet and female speech throughout the entire duration of the audio."}
{"wav": "YbA5zPFSFZAA.wav", "ground_truth_captions": "Static and beeping", "generated_captions": "There is the sound of a power tool drilling throughout the entire duration of the audio, and there's also the sound of mechanisms operating from 9.81 to 10 seconds."}
{"wav": "Y8F-ndyrEWJ8.wav", "ground_truth_captions": "Car is speeding down road, emergency siren is sounding, and a man speaks", "generated_captions": "The audio contains the sound of an emergency vehicle siren and traffic noise."}
{"wav": "YBa92IrXFvJo.wav", "ground_truth_captions": "Cracking and humming from an engine", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "YFhimNYClv40.wav", "ground_truth_captions": "Sirens and a humming engine approach and pass", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a police car siren, and the sound of wind blowing into a microphone."}
{"wav": "YIFRmbxWK8u0.wav", "ground_truth_captions": "A clock ticking", "generated_captions": "There is the ticking of a clock and mechanisms throughout the entire duration of the audio, with brief periods of silence."}
{"wav": "Yi2yhbckq3p0.wav", "ground_truth_captions": "A motorcycle engine running as several vehicle horns honk while a car alarm rings in the distance", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a fire truck siren, and the sound of a car accelerating."}
{"wav": "YkHIe4CfaccQ.wav", "ground_truth_captions": "Continuous basing and rustling", "generated_captions": "The audio contains the sound of paper crumpling and rustling, along with generic impact sounds."}
{"wav": "YlTJLvSvjUZk.wav", "ground_truth_captions": "Whistling to music", "generated_captions": "The audio contains music and whistling sounds."}
{"wav": "YlfAFQ0-wDJU.wav", "ground_truth_captions": "Wind and surf with water splashing", "generated_captions": "The audio contains the sounds of waves, surf, wind noise on microphone, and water splashing."}
{"wav": "Y2JV3emH50XU.wav", "ground_truth_captions": "A vehicle accelerating then driving by as gusts of wind blow and leaves rustle in the distance", "generated_captions": "The audio contains sounds of motor vehicles, specifically cars accelerating and revving their engines."}
{"wav": "YmlnUJH4BQnk.wav", "ground_truth_captions": "Female speech and scratching", "generated_captions": "The audio contains sounds of crumpling paper, mechanisms, and conversation between a female and male speaker."}
{"wav": "YNwoBDrTlbTI.wav", "ground_truth_captions": "A gerbil squeaking during audio static", "generated_captions": "The audio contains the sounds of birds chirping and singing, as well as the noise of something being sprayed."}
{"wav": "Yq3SEOW2m4WY.wav", "ground_truth_captions": "A train horn honks as a train speeds past", "generated_captions": "The audio contains the sound of a train horn blowing and a train passing by."}
{"wav": "Y2UNuMbxz9ds.wav", "ground_truth_captions": "An engine revving and popping", "generated_captions": "The audio contains sounds of an engine idling and revving, as well as generic impact sounds."}
{"wav": "YdYZSKX7vuRI.wav", "ground_truth_captions": "A person snoring loudly followed by a man speaking", "generated_captions": "There is snoring, breathing sounds, and background noise throughout the entire duration of the audio."}
{"wav": "Yek9Fsmm3xqk.wav", "ground_truth_captions": "Splashing with wind blowing hard", "generated_captions": "The audio contains the sounds of waves, surf, wind noise from a microphone, and water splashing."}
{"wav": "YQ87LBiwJjTE.wav", "ground_truth_captions": "Music in the background as a woman speaks and food fries", "generated_captions": "There is the sound of frying food and sizzling, along with female speech throughout the audio."}
{"wav": "YBGEMgl1xjac.wav", "ground_truth_captions": "Various insects and bugs are chirping with a rodent breathing sound in the background", "generated_captions": "There is the sound of birds chirping and tweeting throughout the entire duration of the audio, as well as the sound of water splashing at intervals from 0:18 to 0:23, then again from 0:47 to 0:56, and finally from 1:09 to 1:14."}
{"wav": "Yg6CY7qvu81k.wav", "ground_truth_captions": "Music followed by male speech and distant sizzling", "generated_captions": "There is the sound of frying food, and a man speaking throughout the audio."}
{"wav": "YAR8-MVl_Mf8.wav", "ground_truth_captions": "A man screaming followed by slamming against a metal object proceeded by a man talking cardboard tumbles on a hard surface as a truck engine runs idle in the background", "generated_captions": "The audio contains sounds of mechanisms, generic impact sounds, and surface contact, as well as male speech."}
{"wav": "Y2a6GNu6uCDE.wav", "ground_truth_captions": "A woman delivers a speech", "generated_captions": "The audio contains speech, mechanisms, and surface contact sounds."}
{"wav": "Yc0IggDOisOo.wav", "ground_truth_captions": "Birds chirping, wind blowing, and a bell ringing with faint speech", "generated_captions": "The audio contains bird vocalizations, wind noise, and human speech."}
{"wav": "YbIV3bJZpkgA.wav", "ground_truth_captions": "A helicopter is in flight", "generated_captions": "The audio contains the sound of an engine idling, which is described as medium frequency and lasts for 10 seconds from the start of the recording."}
{"wav": "YynHdcJ9Oqaw.wav", "ground_truth_captions": "Loud booming bursts and whooshes", "generated_captions": "There is a video game sound, an explosion, and gunfire."}
{"wav": "YajheseWZmmU.wav", "ground_truth_captions": "A cat meowing as a person makes kissing noises followed by a guy chuckling", "generated_captions": "There is a dog whimpering and barking, along with background noise throughout the entire duration of the audio."}
{"wav": "YzF3xXn6NTyU.wav", "ground_truth_captions": "Water falling and a woman talks, coughs, then talks again while a man speaks in the background", "generated_captions": "The audio contains sounds of water, mechanisms, and splashing, as well as female speech."}
{"wav": "YUXGzbBGbqAA.wav", "ground_truth_captions": "Footsteps shuffling and fabric slapping a hard surface", "generated_captions": "The audio contains sounds of mechanisms, tapping, and surface contact."}
{"wav": "YvfNKduToki4.wav", "ground_truth_captions": "Truck engines are running, a shrill back-up alarm rings, air brakes engage, and adult males are talking in the background", "generated_captions": "There is the sound of an engine running throughout the audio, and there are also sounds of people talking."}
{"wav": "YKVbmN9ZRg5Q.wav", "ground_truth_captions": "Loud hissing followed by a loud continuous horn and brief clanking", "generated_captions": "The audio contains the sounds of wind blowing, a train horn sounding, and a train moving on tracks."}
{"wav": "YGPj8h-WcjWs.wav", "ground_truth_captions": "Humming of an engine with a woman speaking over a loudspeaker", "generated_captions": "There is the sound of an engine accelerating and revving, as well as male speech throughout the audio."}
{"wav": "Y3ue0gJM0THk.wav", "ground_truth_captions": "Aircraft engine revs and creates propeller which", "generated_captions": "There is the sound of an engine running throughout the entire clip, and there's also the sound of something being rubbed against wood."}
{"wav": "Y5xC4hkAWiao.wav", "ground_truth_captions": "A large motor vehicle engine is idling, then it labors and creaks", "generated_captions": "The audio contains the sound of an engine idling and squealing, which is likely from a car or motorcycle."}
{"wav": "YeRU-rABp8nk.wav", "ground_truth_captions": "Two men talking as a motorcycle engine runs idle and a group of people laugh", "generated_captions": "There is speech, laughter, and the sound of water splashing."}
{"wav": "YTd2EEDdFlRY.wav", "ground_truth_captions": "A man talking as a woman talks in the distance while light music is playing followed by a guitar strumming and footsteps walking on gravel", "generated_captions": "The audio contains sounds of mechanisms, generic impact sounds, and human voices."}
{"wav": "YrbO727iF03I.wav", "ground_truth_captions": "A loud belch followed by male human voices", "generated_captions": "There is a burping sound throughout the entire duration of the audio, and there's also a male voice speaking in English with a fearful mood."}
{"wav": "YZY4aGEniU_E.wav", "ground_truth_captions": "Food and oil sizzling followed by steam hissing as a man talks and light rock music plays in the background", "generated_captions": "There is a continuous hissing noise throughout the audio, and there's also speech by an adult male."}
{"wav": "YKVAIaRPry24.wav", "ground_truth_captions": "Flying insects are buzzing", "generated_captions": "The audio contains the buzzing of insects, specifically bees and wasps."}
{"wav": "YRrmBGjJqlEo.wav", "ground_truth_captions": "Clicking on a keyboard with a man speaking", "generated_captions": "The audio contains sounds of typing on a computer keyboard, male speech, and breathing."}
{"wav": "Yj1AiqT5oHZc.wav", "ground_truth_captions": "Beep then male speaking multiple times", "generated_captions": "The audio contains speech and background noise, with the speech being male singing in English."}
{"wav": "YZ_smJ66Tb3c.wav", "ground_truth_captions": "A man talking as pigeons are cooing and birds are chirping with bird wings flapping", "generated_captions": "The audio contains the sounds of pigeons cooing and flapping their wings, as well as generic impact sounds."}
{"wav": "YDc2WEiRk0rA.wav", "ground_truth_captions": "Hissing spray is occurring, and liquid is pattering on a surface", "generated_captions": "There is the sound of steam hissing throughout the entire duration of the audio, and there's also the sound of a train engine running on railroad tracks from 9.81 to 10.00 seconds."}
{"wav": "YNlKlRKz8OKI.wav", "ground_truth_captions": "A woman talking then laughing followed by plastic tapping and birds chirping in the background", "generated_captions": "The audio contains sounds of birds, specifically ducks and geese, as well as female speech."}
{"wav": "YlVr-PxhZo8s.wav", "ground_truth_captions": "Car engine idling", "generated_captions": "There is an engine idling and knocking, and there's also speech by a male speaking English."}
{"wav": "YzwoqJY03yHE.wav", "ground_truth_captions": "Women speak and a goat bleats", "generated_captions": "There is speech, wind noise, and the sound of water splashing."}
{"wav": "Y1_z6NcidGzM.wav", "ground_truth_captions": "Various speech and a whistle blown and water splashing", "generated_captions": "There is the sound of water splashing, wind blowing into a microphone, and people talking."}
{"wav": "YatmDP_fmK_8.wav", "ground_truth_captions": "A low loud hum gets lower followed by an explosion", "generated_captions": "The audio contains the sound of an aircraft engine running and increasing in intensity, along with wind blowing into a microphone."}
{"wav": "Ye6jSpvTvfJ0.wav", "ground_truth_captions": "Thunder claps and rain falls hard, splashing on surfaces", "generated_captions": "The audio contains the sounds of rain falling and wind blowing into a microphone."}
{"wav": "Ygf6H_MWCqjw.wav", "ground_truth_captions": "A duck quacking followed by camera muffling", "generated_captions": "The audio contains sounds of ducks quacking and water splashing, along with background noise."}
{"wav": "YwnqUgK_-fo4.wav", "ground_truth_captions": "Several loud pops with people cheering", "generated_captions": "There is cheering, clapping, and shouting from a crowd throughout the audio."}
{"wav": "YbQNX7vDalQw.wav", "ground_truth_captions": "A man speaks followed by heavy sizzling", "generated_captions": "There is the sound of frying food and mechanisms throughout, with male speech occurring from 10.68 to 14.52 seconds."}
{"wav": "YSePTNAN7s-w.wav", "ground_truth_captions": "A female speech and then a toilet flushing followed by a female speech.", "generated_captions": "There is a toilet flushing and water draining, as well as a woman speaking throughout the audio."}
{"wav": "YY3lNEe-ZGF0.wav", "ground_truth_captions": "A clock ticking followed by a wooden latch opening", "generated_captions": "The audio contains the ticking of a clock and mechanisms sounds throughout its duration."}
{"wav": "YeJCaRgf1M20.wav", "ground_truth_captions": "A bell chimes followed by camera muffling and metal shuffling then a gear cranking", "generated_captions": "The audio contains the sounds of dishes, pots, and pans clanging, along with mechanisms and generic impact sounds."}
{"wav": "Y-AheI8Epim4.wav", "ground_truth_captions": "Wind noise followed by a tapping noise while people are talking in the background", "generated_captions": "There is wind noise throughout the audio, and speech from 0 to 10 seconds."}
{"wav": "YtmLAXm1WlnE.wav", "ground_truth_captions": "A woman speaks with nearby buzzing of insects", "generated_captions": "The audio contains sounds of mechanisms, wind, and generic impact sounds. There is also speech by both male and female speakers."}
{"wav": "YXamQAY_WXRY.wav", "ground_truth_captions": "A man talking as water splashes and gurgles and a motor engine hums in the background", "generated_captions": "There is the sound of water splashing and gurgling, as well as male speech throughout the duration of the audio."}
{"wav": "YZ-SIyOChVh8.wav", "ground_truth_captions": "Rain and thunder", "generated_captions": "The audio contains the sound of rain falling on a surface and wind blowing into a microphone."}
{"wav": "YwSHzVxdMiTo.wav", "ground_truth_captions": "A pig squeezing and male speech", "generated_captions": "The audio contains sounds of pigs oinking, wind blowing into the microphone, and a man speaking."}
{"wav": "YWCYfCfW9NA0.wav", "ground_truth_captions": "High pitched humming with whooshes of spinning helicopter blades", "generated_captions": "There is the sound of a small engine running throughout the entire duration of the audio, and there's also the sound of wind blowing into a microphone at certain intervals."}
{"wav": "Y-EaZ7EJJUl0.wav", "ground_truth_captions": "A person speaks with distant humming and nearby clinking", "generated_captions": "The audio contains speech, breathing sounds, and background noise."}
{"wav": "YZ3wDry8nnJs.wav", "ground_truth_captions": "Water splashes followed by a girl speaking then scraping followed by spitting", "generated_captions": "There is the sound of water running and splashing, as well as female speech and dog barking."}
{"wav": "YwOFBldBFRNk.wav", "ground_truth_captions": "Church bells ringing as rain pours and wind blows into a microphone", "generated_captions": "The audio contains the sound of change ringing, which is a method of campanology where bells are rung in a series of mathematical patterns called 'changes'."}
{"wav": "YnLZeG9LaLgw.wav", "ground_truth_captions": "Loud humming of a car speeding into the distance with wind blowing and tires squealing", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with music playing in the background."}
{"wav": "Y_z-bidQYVao.wav", "ground_truth_captions": "Male rapping and screaming", "generated_captions": "The audio contains music and rapping."}
{"wav": "Y1QNLMF-Kl_s.wav", "ground_truth_captions": "A woman is giving a speech", "generated_captions": "The audio contains speech by a female speaker and background noise throughout the entire duration of the recording."}
{"wav": "Y7XUt6sQS7nM.wav", "ground_truth_captions": "Sheep baaing with young female voice and wind gusts", "generated_captions": "The audio contains sounds of sheep bleating, wind blowing into the microphone, and laughter."}
{"wav": "Ycz0FSQDVBMw.wav", "ground_truth_captions": "Hissing and chugging with brief muffled speech", "generated_captions": "The audio contains the sound of steam hissing and people talking."}
{"wav": "YS_3aeOvniZc.wav", "ground_truth_captions": "A race car is accelerating and shifting gears", "generated_captions": "The audio contains sounds of race car engines revving and tires squealing, along with the sound of acceleration."}
{"wav": "YSZ6CcXINiiE.wav", "ground_truth_captions": "A man speaks followed by a loud bursts and then laughter", "generated_captions": "There is speech, laughter, and coughing sounds throughout the audio."}
{"wav": "YfBYDJWChe5c.wav", "ground_truth_captions": "A person snoring", "generated_captions": "There is snoring and breathing sounds throughout the audio, with occasional impact sounds."}
{"wav": "YJC2ZrXzCX4Y.wav", "ground_truth_captions": "A person snores while people communicate", "generated_captions": "There is snoring and breathing sounds throughout the audio, with background noise of mechanisms."}
{"wav": "Yvsy1IpYmrSY.wav", "ground_truth_captions": "Tires squealing and an engine revving repeatedly", "generated_captions": "The audio contains the sound of a car accelerating and revving its engine, as well as the sound of wind blowing into a microphone."}
{"wav": "YTgxst7Ft9js.wav", "ground_truth_captions": "Sanding and filing then a man speaks", "generated_captions": "There is a man speaking and sanding sounds throughout the audio."}
{"wav": "Y5YzNSjmZ3Wg.wav", "ground_truth_captions": "A nearby insect buzzes with nearby vibrations", "generated_captions": "The audio contains sounds of buzzing insects, specifically bees and wasps, as well as birds chirping."}
{"wav": "YD2Xc_jZllDY.wav", "ground_truth_captions": "Dog barking with win and man speaking", "generated_captions": "The audio contains sounds of dogs barking, mechanisms, and human speech."}
{"wav": "YOxUVcZmeiyI.wav", "ground_truth_captions": "A clock ticktocks with music", "generated_captions": "The audio contains the ticking of a clock and the chiming of bells, which is reminiscent of a music box."}
{"wav": "YkXjzsroVTtw.wav", "ground_truth_captions": "Birds chirp and sing in the background, while an adult male speaks and crunching footfalls occur", "generated_captions": "There is bird chirping, tweeting and cooing sounds throughout the audio. There's also a man speaking from 4.58 to 7.13 seconds."}
{"wav": "Y14izd_i3ryE.wav", "ground_truth_captions": "A man speaks as an engine runs and wind rushes by, another man speaks over a loudspeaker", "generated_captions": "There is a man speaking, an engine running, and wind blowing throughout the audio."}
{"wav": "Y4YodC6RnplI.wav", "ground_truth_captions": "A female laughs, snoring occurs, and an adult male speaks in the background", "generated_captions": "There is snoring, breathing sounds, and laughter throughout the audio."}
{"wav": "YIsUG5SKWNZA.wav", "ground_truth_captions": "A woman whispering then talking as an infant cries followed by a man yelling", "generated_captions": "There is crying, breathing sounds, and mechanisms throughout the entire duration of the audio."}
{"wav": "YSL3wB5sDcdw.wav", "ground_truth_captions": "Leaves rustling as a leaf blower operates and wind blows into a microphone", "generated_captions": "The audio contains the sound of wind blowing and waves crashing, which is categorized as natural sounds."}
{"wav": "YfmEft49sPfE.wav", "ground_truth_captions": "A man is speaking with the wind blowing in the background", "generated_captions": "The audio contains speech by a male speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YwFiCblfZ-vg.wav", "ground_truth_captions": "A man speaking followed by another man speaking in the background during audio static", "generated_captions": "The audio contains speech by a male speaker, who speaks in French."}
{"wav": "YsbW7XwwUtSU.wav", "ground_truth_captions": "A clock ticking repeatedly", "generated_captions": "The audio contains the ticking of a clock and mechanisms sounds throughout its duration."}
{"wav": "YmYQrjcYNrW0.wav", "ground_truth_captions": "A bus horn honking as wind is blowing into a microphone before a bus drives by", "generated_captions": "The audio contains the sound of a train passing by and blowing its horn multiple times."}
{"wav": "YkagkXkAVPNo.wav", "ground_truth_captions": "An engine revving followed by a loud honk, then several other honks and a woman talking", "generated_captions": "The audio contains the sound of a vehicle engine running and a horn honking several times."}
{"wav": "Y8VOibo9Q_Dc.wav", "ground_truth_captions": "Water splashing and birds chirping", "generated_captions": "The audio contains the sound of water running and splashing, as well as mechanisms operating."}
{"wav": "YW7OJevEgq7w.wav", "ground_truth_captions": "A dog whimpering and barking while breathing rapidly", "generated_captions": "The audio contains sounds of dogs barking and howling, as well as background noise."}
{"wav": "YpO8kbg9IJnc.wav", "ground_truth_captions": "Some light clicks followed by a man speaking and water splashing", "generated_captions": "There is the sound of water running and splashing, as well as male speech."}
{"wav": "Y3XcIVh40pTI.wav", "ground_truth_captions": "A person is snoring steadily", "generated_captions": "There is snoring and breathing sounds throughout the entire duration of the audio, with no other significant sound events detected."}
{"wav": "YnLtNjMimLE0.wav", "ground_truth_captions": "Running and splashing water", "generated_captions": "The audio contains the sound of water falling into a pool, which is identified as a waterfall."}
{"wav": "YESjMIqrvRj4.wav", "ground_truth_captions": "Rain pitter-patters as thunder cracks and the wind blows", "generated_captions": "The audio contains rain falling on a surface, wind blowing into a microphone, and waves crashing sounds."}
{"wav": "Y5t6tSW0yT40.wav", "ground_truth_captions": "A motor hums softly followed by spraying", "generated_captions": "The audio contains the sound of an aircraft engine running and accelerating, along with generic impact sounds."}
{"wav": "YmUGmCSNETcg.wav", "ground_truth_captions": "Women talk while food fries", "generated_captions": "There is the sound of sizzling food and frying, along with female speech throughout the duration of the audio."}
{"wav": "Y096oTVzc5Gs.wav", "ground_truth_captions": "An adult female speaks and an animal growls playfully", "generated_captions": "There is a child speaking and singing, mechanisms sounds, and surface contact sounds throughout the audio."}
{"wav": "YAUmY0YRAFQE.wav", "ground_truth_captions": "Sirens ring as a vehicle speeds past", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a police car siren, and the sound of wind blowing into a microphone."}
{"wav": "Y8Zo30kV5aiI.wav", "ground_truth_captions": "Emergency vehicle siren passing by then fading", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a police car siren, and background noise."}
{"wav": "YPvWI4p74UOs.wav", "ground_truth_captions": "Laughing and birds chirping with wind and an engine running", "generated_captions": "The audio contains sounds of wind blowing, ducks quacking, and people talking."}
{"wav": "YH7-orYrKBeo.wav", "ground_truth_captions": "A group of people talking as an infant cries while a muffled bus engine runs", "generated_captions": "The audio contains sounds of children shouting, crying, and speaking, as well as background noise throughout the entire duration."}
{"wav": "YPZBUdlKwX04.wav", "ground_truth_captions": "A plastic clack followed by a man talking as a stream of water rushes and a crowd of people talk in the background", "generated_captions": "There is the sound of water flowing and people talking throughout the audio."}
{"wav": "YTaQKhIRwii4.wav", "ground_truth_captions": "A crowd of people applauding followed by a woman speaking", "generated_captions": "The audio contains the sound of an audience applauding, followed by a male singing."}
{"wav": "YAgh2EKINlSw.wav", "ground_truth_captions": "Hard rain falls on a metal surface, then three adult males speak while soft rhythmic whooshing occurs", "generated_captions": "The audio contains the sounds of rain falling on a surface and wind blowing into a microphone."}
{"wav": "Yk4XyfaWVLEY.wav", "ground_truth_captions": "A vehicle engine idles and birds chirp in the background", "generated_captions": "The audio contains the sound of an engine idling and birds chirping."}
{"wav": "YROootH-mtEI.wav", "ground_truth_captions": "A river stream flowing rapidly", "generated_captions": "The audio contains the sound of water flowing from a waterfall and a stream."}
{"wav": "YAxd__X2rixk.wav", "ground_truth_captions": "Clip clops of a horse running by", "generated_captions": "The audio contains the sounds of rain falling on a hard surface and the sound of hooves clip-clopping."}
{"wav": "YnaPgJvWTIY4.wav", "ground_truth_captions": "A motorbike running idle then revving", "generated_captions": "The audio contains the sound of an engine idling, which is a medium frequency engine noise."}
{"wav": "YBMayJId0X1s.wav", "ground_truth_captions": "A man talking as a baby is crying", "generated_captions": "There is crying, babbling, and breathing sounds throughout the audio clip."}
{"wav": "Y5I8lmN8rwDM.wav", "ground_truth_captions": "A power tool sanding", "generated_captions": "There is the sound of steam hissing and people talking in the background throughout the entire duration of the audio."}
{"wav": "YhVUmQfBIYe8.wav", "ground_truth_captions": "A man speaks followed by a door opening", "generated_captions": "The audio contains speech by a male speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YP12nvSpKXcs.wav", "ground_truth_captions": "Birds are calling and many bees are buzzing, then a child speaks briefly and rustling footfalls and rattling occur", "generated_captions": "The audio contains sounds of birds chirping, insects buzzing, and a fly buzzing."}
{"wav": "YxpZna_FwDhI.wav", "ground_truth_captions": "A click is followed by a woman speaking and then a sewing machine stitching", "generated_captions": "There is crumpling and crinkling sounds, mechanisms, and surface contact sounds throughout the audio. There are also female speech segments at various intervals."}
{"wav": "Y9dLLsZVRSZI.wav", "ground_truth_captions": "Engine idling continuously followed by honking", "generated_captions": "The audio contains the sound of an aircraft engine idling, which is described as loud and continuous throughout the clip."}
{"wav": "YKJKHDKKW3XU.wav", "ground_truth_captions": "Gurgling and splashing water", "generated_captions": "The audio contains the sounds of water splashing and gurgling, as well as mechanisms operating."}
{"wav": "YEBCH7TPgiPc.wav", "ground_truth_captions": "Engine revs very high for a while, then begins to slow down", "generated_captions": "The audio contains the sound of an engine revving and accelerating, specifically a medium frequency engine."}
{"wav": "YSCow4mpBsGY.wav", "ground_truth_captions": "A person is snoring", "generated_captions": "The audio contains sounds of mechanisms, breathing, and snoring."}
{"wav": "Y-BUWGM7qeUM.wav", "ground_truth_captions": "Rain is heard falling", "generated_captions": "The audio contains the sounds of rain and thunder."}
{"wav": "YhFCmq9pCBbM.wav", "ground_truth_captions": "A girl speaking with plastic crinkling", "generated_captions": "The audio contains the sounds of paper crumpling and tearing, as well as female speech."}
{"wav": "Y9b6RqajfAmw.wav", "ground_truth_captions": "Birds chirping together with rustling", "generated_captions": "The audio contains bird vocalizations and chirping, wind blowing into the microphone, and mechanisms sounds."}
{"wav": "YD4s5aHrsBgs.wav", "ground_truth_captions": "A person whistles to music", "generated_captions": "The audio contains whistling sounds, music playing, and background noise."}
{"wav": "Y404cD3bVXDc.wav", "ground_truth_captions": "A baby crying with a television on in background", "generated_captions": "There is a baby crying and babbling, along with some background noise throughout the entire duration of the audio."}
{"wav": "YI4HpYGMMsz4.wav", "ground_truth_captions": "A man speaking with slapping on a wooden surface as compressed air hisses in the background", "generated_captions": "The audio contains speech, background noise, and bird chirping sounds."}
{"wav": "Y83j4GgHXTLE.wav", "ground_truth_captions": "A kid laughing and screaming with a man chuckling and woman whispering", "generated_captions": "There is a baby laughing and babbling, along with some background noise throughout the audio."}
{"wav": "YuY4fe5DT1gI.wav", "ground_truth_captions": "A person is typing on a computer keyboard", "generated_captions": "The audio contains the sounds of typing on a computer keyboard and mechanisms."}
{"wav": "Y-CcGuq0yoKo.wav", "ground_truth_captions": "A woman speaking on a microphone as a kid yells in the distance with periodic audio static clicks", "generated_captions": "The audio contains sounds of children speaking, mechanisms, and breathing."}
{"wav": "YWUyeFOyKIg0.wav", "ground_truth_captions": "Wind and people speaking and a car passing by", "generated_captions": "The audio contains sounds of motor vehicles, specifically cars and trucks, as well as male speech."}
{"wav": "YQt0_xTadAT0.wav", "ground_truth_captions": "A group of frogs croaking as plastic flutters in the background", "generated_captions": "There is a frog croaking throughout the entire duration of the audio, and birds chirping in the background from 9.85 to 10.0 seconds."}
{"wav": "Y9zstu_IfAm4.wav", "ground_truth_captions": "A truck horn honking as a large truck engine drives by while a crowd of people talk in the background", "generated_captions": "The audio contains the sound of a vehicle horn honking and traffic noise."}
{"wav": "YaZAXO2WZn84.wav", "ground_truth_captions": "A train running on railroad tracks followed by a lawn mower engine running then a steam engine whistle blowing as a crowd of people are talking in the background", "generated_captions": "There is the sound of a train horn blowing and a train running on tracks throughout the entire duration of the audio, as well as people talking in the background."}
{"wav": "Y466ucPGoNSQ.wav", "ground_truth_captions": "A speech and then a cat vocalizing repeatedly", "generated_captions": "There is speech, mechanisms, and ticking sounds throughout the audio."}
{"wav": "YFf8bCCJfVX4.wav", "ground_truth_captions": "An air gun firing rapidly followed by plastic rattling and a young boy talking while footsteps walk over grass", "generated_captions": "The audio contains the sounds of gunfire, machine gun fire, and cap guns being fired."}
{"wav": "YUAmDLPjNyMg.wav", "ground_truth_captions": "An aircraft flying as a person briefly sniffs aloud while wind blows into a microphone", "generated_captions": "The audio contains the sound of an aircraft engine running and wind blowing into a microphone."}
{"wav": "Y0qbHT34qTZE.wav", "ground_truth_captions": "Male yelling and multiple gunshots", "generated_captions": "The audio contains video game sounds, male speech, and gunshots."}
{"wav": "YwAZrOPvul4Y.wav", "ground_truth_captions": "A man talking as plastic is crinkling", "generated_captions": "There is crumpling and crinkling sounds, mechanisms, and male speech throughout the audio."}
{"wav": "Yt4prXmPwthg.wav", "ground_truth_captions": "Vibrations from a running sewing machine with a woman speaking", "generated_captions": "There is the sound of an engine idling throughout the entire clip, and there's also speech occurring from 4.98 to 5.76 seconds."}
{"wav": "Y-R69Fa-mCaY.wav", "ground_truth_captions": "A chainsaw cutting as wood cracks and creaks", "generated_captions": "The audio contains the sound of a chainsaw cutting through wood, which is classified as a power tool."}
{"wav": "Y3XuyGJqaXv8.wav", "ground_truth_captions": "A man speaks over a loudspeaker with a crowd talking in the distance and dogs barking", "generated_captions": "The audio contains sounds of male speech, hubbub, and cheering."}
{"wav": "Ym_U506sf9p4.wav", "ground_truth_captions": "A woman talking followed by plastic thumping then metal clanking as food and oil sizzles", "generated_captions": "There is the sound of food sizzling and frying, along with female speech throughout the duration of the audio."}
{"wav": "YC9NC7wJ7C3w.wav", "ground_truth_captions": "A woman speaking continuously", "generated_captions": "The audio contains speech and breathing sounds, with the woman speaking in French."}
{"wav": "YT9_ep-3BZDY.wav", "ground_truth_captions": "A woman speaks followed by crinkling", "generated_captions": "The audio contains sounds of paper rustling, breathing, and surface contact."}
{"wav": "Y7_smJ8VbfSU.wav", "ground_truth_captions": "Female speaking", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YFXdoNvmrYxo.wav", "ground_truth_captions": "A young girl talking followed by a man talking then a young boy softly talking as birds are chirping in the background", "generated_captions": "The audio contains bird vocalizations, mechanisms, and child speech."}
{"wav": "YhiJB_95IWiE.wav", "ground_truth_captions": "Male speech and then scraping", "generated_captions": "The audio contains sounds of crumpling paper, mechanisms, and male speech."}
{"wav": "Ya3GzZKxUTy8.wav", "ground_truth_captions": "Birds chirping and then a dog barking and a duck quaking", "generated_captions": "The audio contains sounds of birds chirping, ducks quacking, and wind blowing into the microphone."}
{"wav": "Y2bq2lc3DLwM.wav", "ground_truth_captions": "A man speaking and a car driving closer than passing by", "generated_captions": "The audio contains sounds of mechanisms, motor vehicles (road), and a car passing by."}
{"wav": "Y6CDl4CqOgMg.wav", "ground_truth_captions": "An animal heavily breathing then snorting followed by footsteps on a hard surface and a camera muffling", "generated_captions": "There is snoring and breathing sounds throughout the audio, with occasional impact sounds."}
{"wav": "YmWqH2xwjkYA.wav", "ground_truth_captions": "A baby laughs and a woman speaks", "generated_captions": "There is a baby laughing and babbling, along with some background noise throughout the entire duration of the audio."}
{"wav": "Y8IdCiapDYCU.wav", "ground_truth_captions": "A few electronic-sounding animal noises followed by barking from a small dog", "generated_captions": "There is the sound of dogs barking and growling, rain falling on a surface, and a woman speaking."}
{"wav": "YDn3buZWMzwY.wav", "ground_truth_captions": "A man and a kid laughing followed by another man speaking as a person snores", "generated_captions": "There is a baby laughing and burping, along with some background noise throughout the entire duration of the audio."}
{"wav": "YyLu4b01t53k.wav", "ground_truth_captions": "The loud idling of a machine", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "Y2sZhC_mKeic.wav", "ground_truth_captions": "A cat meowing followed by metal clacking as a water sprinkler sprays in the background", "generated_captions": "There is a cat meowing and birds chirping throughout the audio, along with some background noise."}
{"wav": "YtTB0BK39JI8.wav", "ground_truth_captions": "Bells ring followed by clanking", "generated_captions": "The audio contains the sound of change ringing, which is a method of ringing bells in a series of mathematical patterns called 'changes'."}
{"wav": "YsqWyxUObwkw.wav", "ground_truth_captions": "A boat engine starts up and idles", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "YYH4qi8Ul6v0.wav", "ground_truth_captions": "A man talking as an infant is crying followed by a man humming", "generated_captions": "There is a baby crying, a woman speaking, and background noise throughout the audio."}
{"wav": "YHqndxoujCYI.wav", "ground_truth_captions": "A bell chiming as a clock ticks and a man talks through a television speaker in the background followed by a muffled bell chiming", "generated_captions": "The audio contains the sound of change ringing, also known as campanology, which is the art of ringing a set of tuned bells in a controlled way."}
{"wav": "YL6rnV0oNIII.wav", "ground_truth_captions": "Laser followed by a gun shot", "generated_captions": "The audio contains electronic music and video game sounds, specifically featuring a laser blast."}
{"wav": "YsI7_ycEYzAY.wav", "ground_truth_captions": "A clock ticks repeatedly", "generated_captions": "The audio contains the ticking of a clock and mechanisms sounds throughout its duration."}
{"wav": "YAFgGoY8Ihhg.wav", "ground_truth_captions": "Wind blowing and a siren rings", "generated_captions": "There is the sound of wind blowing and a vehicle passing by."}
{"wav": "Y1L_OyngNZMA.wav", "ground_truth_captions": "Two men talking on a microphone as a crowd of people laugh and applaud", "generated_captions": "The audio contains sounds of male speech, laughter, and clapping."}
{"wav": "YU5ij0M7T-hk.wav", "ground_truth_captions": "Footsteps and scuffing occur, after which a door grinds, squeaks and clicks, an adult male speaks, and the door grinds, squeaks and clicks shut with a thump", "generated_captions": "The audio contains the sounds of mechanisms, generic impact sounds, and surface contact."}
{"wav": "YCbe2B6ohBpw.wav", "ground_truth_captions": "Continuous quacking and rustling", "generated_captions": "There is the sound of ducks quacking throughout the entire duration of the audio, and there's also a brief moment where something is being tapped."}
{"wav": "YFlk-X0gwjF4.wav", "ground_truth_captions": "Birds are chirping and singing, rustling occurs and an adult male speaks briefly in the foreground, and an adult male speaks in the background", "generated_captions": "The audio contains bird vocalizations, insect sounds, and generic impact sounds."}
{"wav": "Y-mb4Fw4Z0xg.wav", "ground_truth_captions": "A car engine accelerating and then laughter", "generated_captions": "The audio contains sounds of race cars accelerating and revving, as well as male speech."}
{"wav": "Ym_NCf-q4Gn0.wav", "ground_truth_captions": "Plastic thumping as an idle motorcycle engine runs", "generated_captions": "The audio contains the sound of an engine idling, specifically from a motorcycle."}
{"wav": "Y6aWnK1GyeJY.wav", "ground_truth_captions": "A baby is crying and a person sneezes then another person speaks", "generated_captions": "The audio contains sounds of human voice, crying baby, and breathing."}
{"wav": "Y2ceUOv8A3FE.wav", "ground_truth_captions": "A train horn blowing multiple times as a train runs on railroad tracks while a man and a young kid talk in the background alongside birds cooing in the distance", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a fire engine or fire truck siren, and the sound of a train horn blowing."}
{"wav": "YRk-ujWKzPuc.wav", "ground_truth_captions": "Hard rain is falling and splashing on a surface", "generated_captions": "The audio contains the sound of rain falling on a surface and wind blowing into a microphone."}
{"wav": "YoiIi6H83Y38.wav", "ground_truth_captions": "A motorbike engine starting up then revving as a man talks in the background", "generated_captions": "The audio contains the sound of an engine accelerating and revving, as well as male speech."}
{"wav": "Y5ORpSk5CIWc.wav", "ground_truth_captions": "Humming of a small engine passing by", "generated_captions": "The audio contains the sound of an engine revving and accelerating, specifically from 0:00 to 10:00 seconds."}
{"wav": "Yf8WPf5F22xI.wav", "ground_truth_captions": "Sneezing followed by a ticking clock and a man speaking", "generated_captions": "There is a man speaking, breathing heavily, and snoring sounds throughout the audio."}
{"wav": "Y1ed87LLY97k.wav", "ground_truth_captions": "A fan sound and a tapping noise", "generated_captions": "The audio contains the sound of an engine idling and then being turned off, along with background noise."}
{"wav": "YFeHndzYAUkg.wav", "ground_truth_captions": "A power tool drilling as rock music plays", "generated_captions": "The audio contains music playing throughout, with a guitar solo starting at 10 seconds and ending at the end of the clip."}
{"wav": "Yne2DpKCIr4Y.wav", "ground_truth_captions": "Ocean waves crashing as wind blows into a microphone", "generated_captions": "The audio contains the sound of waves crashing and wind blowing into a microphone."}
{"wav": "YAj_VMUSNjNM.wav", "ground_truth_captions": "Engine revving louder and louder than eases down", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with medium frequency sounds throughout."}
{"wav": "Y-SkjbQVgJ0M.wav", "ground_truth_captions": "A car passes by shortly after a man starts talking", "generated_captions": "There is the sound of an engine accelerating and tires squealing throughout the audio, along with background noise."}
{"wav": "Y1a2XWJ8NA_Q.wav", "ground_truth_captions": "A motorboat engine running as two women are talking and wind is blowing into a microphone", "generated_captions": "The audio contains the sounds of wind blowing and water splashing, along with male speech."}
{"wav": "YVMsbrcHPBfk.wav", "ground_truth_captions": "A man mimics a goat bleating", "generated_captions": "The audio contains sounds of birds chirping, ducks quacking, and people talking."}
{"wav": "YoZaEHkfh5Eg.wav", "ground_truth_captions": "A vehicle horn honking during a series of electronic beeps", "generated_captions": "The audio contains the sound of an air horn being blown repeatedly, which is typically associated with a truck or large vehicle."}
{"wav": "YZ7yDwpdGelM.wav", "ground_truth_captions": "A man speaking followed by sawing then plastic crinkling as water trickles", "generated_captions": "There is the sound of frying food and sizzling, as well as male speech throughout the audio."}
{"wav": "YkF1KWybdRpM.wav", "ground_truth_captions": "Aircraft engine roars as it approaches and then recedes", "generated_captions": "The audio contains the sound of an aircraft engine running and wind blowing into a microphone."}
{"wav": "YCMNlIW6Lkwc.wav", "ground_truth_captions": "A man is talking while plastic clacks followed by a popping explosion then a group of people talking and laughing", "generated_captions": "The audio contains sounds of conversation, laughter, and clapping."}
{"wav": "Y0yETgW44MZU.wav", "ground_truth_captions": "A train sounds horn while the engine taps", "generated_captions": "The audio contains the sound of a train horn blowing, wind blowing into a microphone, and an emergency vehicle siren."}
{"wav": "Y67BsqRkh-dU.wav", "ground_truth_captions": "A toilet is flushed", "generated_captions": "There is the sound of water running and splashing throughout the entire duration of the audio, along with some background noise."}
{"wav": "Y1HCuBnPLMqQ.wav", "ground_truth_captions": "A liquid makes a trickling noise", "generated_captions": "There is the sound of water running and dripping, along with mechanisms operating throughout the duration of the audio."}
{"wav": "YLBe33dw9ezg.wav", "ground_truth_captions": "Buzzing sound moving nearer and further", "generated_captions": "There is the sound of an electric toothbrush being used throughout the entire clip, and there's also the sound of something vibrating."}
{"wav": "Y0Dt-pH0pW-Y.wav", "ground_truth_captions": "A motorcycle running and male speech and then laughing", "generated_captions": "The audio contains sounds of an engine accelerating, revving, and vrooming, as well as male speech."}
{"wav": "YGE1aZSnPr2Q.wav", "ground_truth_captions": "A man laughing", "generated_captions": "There is laughter, speech, and breathing sounds throughout the audio."}
{"wav": "YTOaQMYc79Mw.wav", "ground_truth_captions": "A vehicle struggling to start with some clicks and whines", "generated_captions": "The audio contains sounds of mechanisms, wind noise from the microphone, camera sounds, and generic impact sounds."}
{"wav": "YKJhGuhNHToA.wav", "ground_truth_captions": "Brief silence followed by wood shuffling on a stone surface", "generated_captions": "The audio contains the sounds of mechanisms, fire, and surface contact."}
{"wav": "YKnsKf9KoNds.wav", "ground_truth_captions": "A man speaks nearby and another speaks over the phone", "generated_captions": "The audio contains speech and background noise."}
{"wav": "Y9E8BmPZ9mWc.wav", "ground_truth_captions": "A truck engine running as a group of men are talking", "generated_captions": "There is an engine idling throughout the audio, and there are sounds of people talking."}
{"wav": "YmJ6ZO3xEcgw.wav", "ground_truth_captions": "A woman sneezing repeatedly", "generated_captions": "There is a sound of someone crying and breathing heavily throughout the entire duration of the audio, from 0 to 10 seconds."}
{"wav": "YVkbp8VmL3pM.wav", "ground_truth_captions": "An infant crying as clothes rustle", "generated_captions": "There is a baby crying and mechanisms sounds throughout the audio, with breathing sounds occurring at intervals from 9.82 to 10.00 seconds."}
{"wav": "YCBwXKOpJY_o.wav", "ground_truth_captions": "A woman and young boy talking", "generated_captions": "The audio contains speech by a female speaker and background noise."}
{"wav": "Y8ipe6b1LwHQ.wav", "ground_truth_captions": "A glass link occurs, a thump, and then clattering", "generated_captions": "The audio contains the sounds of dishes, pots, and pans clattering, along with generic impact sounds."}
{"wav": "Yyrxa6_P2I80.wav", "ground_truth_captions": "Several birds chirping and pigeons cooing", "generated_captions": "The audio contains bird vocalizations, chirping and cooing sounds throughout the entire duration of the clip."}
{"wav": "YA0E_UiD-fR4.wav", "ground_truth_captions": "Digital beeping followed by rapid vibrations and humming", "generated_captions": "There is the sound of a small motor running throughout the entire clip, and there's also the sound of wood being sawed from 8.95 to 10 seconds into the recording."}
{"wav": "Y0G7rb74R-2A.wav", "ground_truth_captions": "A man speaking on a microphone as a crowd of people laugh followed by dinner plates clacking", "generated_captions": "There is laughter, speech, and background noise throughout the audio."}
{"wav": "YLvhvAA11oxE.wav", "ground_truth_captions": "A vehicle engine repeatedly revving as tires skid while a man talks over an intercom and wind blows into a microphone", "generated_captions": "The audio contains sounds of motor vehicles, specifically cars accelerating and revving their engines."}
{"wav": "YCMUuelJFJ7Q.wav", "ground_truth_captions": "A bell ringing followed by a clock ticking", "generated_captions": "The audio contains the sound of a church bell ringing and mechanisms."}
{"wav": "YNmmbNqmsPaY.wav", "ground_truth_captions": "An engine idling with bells ringing in the background", "generated_captions": "The audio contains the sound of an engine idling and a medium frequency engine running."}
{"wav": "YjinJkonlrWc.wav", "ground_truth_captions": "An engine running and muffled speech", "generated_captions": "There is an aircraft engine running, and there's also the sound of a man speaking."}
{"wav": "YR_g4RpU9mO0.wav", "ground_truth_captions": "A motorboat engine running idle then accelerating as water trickles followed by water spraying", "generated_captions": "The audio contains the sound of an engine idling and wind blowing into a microphone."}
{"wav": "Y1wW0YJQ-Xa0.wav", "ground_truth_captions": "A person coughing followed by a series of compressed air sprays as tin and plastic rattle then a man speaking as a crowd of people talk in the background", "generated_captions": "The audio contains mechanisms, surface contact sounds, and male speech."}
{"wav": "YBOB65Nd0pXo.wav", "ground_truth_captions": "A helicopter engine operating while wind blows heavily into a microphone", "generated_captions": "The audio contains the sound of an aircraft engine running and wind blowing into a microphone."}
{"wav": "YxbLW9Wt1Jsg.wav", "ground_truth_captions": "Some rustling with short bursts of vibrations from a sewing machine", "generated_captions": "The audio contains the sounds of mechanisms, specifically a sewing machine and a cash register."}
{"wav": "Y3ndid3jni7M.wav", "ground_truth_captions": "A loud horn honking followed by a bell ringing together with clickety-clacking train passing by", "generated_captions": "The audio contains the sound of a train approaching and blowing its horn, as well as wind noise picked up by the microphone."}
{"wav": "YtJhVH3VIrnE.wav", "ground_truth_captions": "A object is hitting a surface followed by a loud boom", "generated_captions": "The audio contains the sounds of firecrackers popping and fizzing, as well as generic impact sounds."}
{"wav": "YyRoKi7rhSRo.wav", "ground_truth_captions": "A toilet flushes and water drains", "generated_captions": "The audio contains the sound of water running from a faucet and splashing into a sink, as well as generic impact sounds."}
{"wav": "Y2msevPMQB4M.wav", "ground_truth_captions": "A power tool vibrating and humming", "generated_captions": "There is the sound of a power tool drilling throughout the entire duration of the audio, and there's also the sound of wood being sawed from 9.48 to 10.00 seconds."}
{"wav": "Y7MLERaOgK_Y.wav", "ground_truth_captions": "A girl sings while a sewing machine stitches and then speaks when it stops", "generated_captions": "There is music playing throughout the audio, and there are sounds of mechanisms, surface contact, and ratchet and pawl gears."}
{"wav": "YnuZEAuAl8hQ.wav", "ground_truth_captions": "A duck quacking as wind lightly blows and water splats in the distance", "generated_captions": "The audio contains sounds of ducks quacking, wind blowing into the microphone, water splashing and gurgling, and birds chirping."}
{"wav": "YOVQMFBeCHq0.wav", "ground_truth_captions": "Low frequency emergency siren going off followed by the siren slowing briefly", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a police car siren, and background noise."}
{"wav": "YXz56Q2Q5j5c.wav", "ground_truth_captions": "Wood being scraped along with mechanical sounds", "generated_captions": "There is the sound of wood being rubbed and tapped, as well as mechanisms throughout the entire duration of the audio."}
{"wav": "Y9z2OwpftxUE.wav", "ground_truth_captions": "Heavy wind and thunder", "generated_captions": "The audio contains the sounds of waves, surf, and wind blowing into a microphone."}
{"wav": "Yn4VktYihtJU.wav", "ground_truth_captions": "Strong gusts of wind are followed by cheers and shouts from several people plus the chatter of girl", "generated_captions": "There is cheering, shouting, and wind noise throughout the audio."}
{"wav": "Y0_K6OKtoBBU.wav", "ground_truth_captions": "A cat is meowing", "generated_captions": "There is a cat meowing and caterwauling throughout the entire duration of the audio, along with sounds of mechanisms and wind blowing into a microphone."}
{"wav": "Y9hxFqltp3xw.wav", "ground_truth_captions": "A woman speaking followed by spraying", "generated_captions": "The audio contains speech by a female speaker and background noise throughout the entire duration of the recording."}
{"wav": "YLvMA1Wcgu3w.wav", "ground_truth_captions": "A man talking followed by plastic creaking and clacking as frogs croak and crickets chirp", "generated_captions": "The audio contains bird vocalizations, insect sounds, and frog croaks throughout the entire duration of the recording. Additionally, there is speech from 0:01 to 2:59 seconds."}
{"wav": "YW4GEwnXc9tQ.wav", "ground_truth_captions": "While music plays in the background, a frog croaks, young females speak and laugh, and a young male speaks", "generated_captions": "The audio contains sounds of mechanisms, generic impact sounds, human voice, laughter, and music."}
{"wav": "YHxZADVzNIqs.wav", "ground_truth_captions": "Birds chirping and water dripping with some banging in the background", "generated_captions": "The audio contains sounds of birds chirping, water trickling and dripping, and a duck quacking."}
{"wav": "Y9vZDsGjyh5M.wav", "ground_truth_captions": "Vehicle motor running", "generated_captions": "There is the sound of an engine idling throughout the entire duration of the audio, and there's also the sound of mechanisms operating from 0 to 10 seconds."}
{"wav": "Y9MgGaTbmc6g.wav", "ground_truth_captions": "A vehicle revving and accelerating as tires skid and squeak on a road", "generated_captions": "The audio contains sounds of a car accelerating and skidding, along with wind blowing into the microphone."}
{"wav": "YlX3k5p2I_g0.wav", "ground_truth_captions": "Man talking in the wind and someone yells in the background while an engine makes squealing and air puffing sounds", "generated_captions": "There is speech, wind noise, and the sound of an aircraft engine running throughout the audio."}
{"wav": "Yeu5bq0A3XVQ.wav", "ground_truth_captions": "A male voice talks after doing some burps", "generated_captions": "There is a loud burp and a man speaking in the background."}
{"wav": "YjYPU6aSDo88.wav", "ground_truth_captions": "An airplane engine and then light talking", "generated_captions": "The audio contains the sound of an aircraft engine accelerating and then idling, along with wind blowing into a microphone."}
{"wav": "YEcihYbSlyck.wav", "ground_truth_captions": "Vehicles are moving, horns are sounding, the door alarm to a bus is beeping", "generated_captions": "The audio contains the sounds of a large motor vehicle engine running, air brakes releasing, and a train horn blowing."}
{"wav": "YFJkvAMLmejY.wav", "ground_truth_captions": "People whisper and then a horn sounds and people laugh", "generated_captions": "There is a harmonica playing, background noise, and laughter throughout the audio."}
{"wav": "YmVjub3o_IxE.wav", "ground_truth_captions": "Constant squeaking occurs while a man speaks", "generated_captions": "There is a man speaking throughout the audio, and there are sounds of frogs croaking and insects chirping."}
{"wav": "YQRtuOWWya30.wav", "ground_truth_captions": "Metal clacking followed by a man talking as metal rattles while light guitar music plays in the background", "generated_captions": "The audio contains sounds of mechanisms, coins dropping, and male speech."}
{"wav": "YBn4lc01q9vE.wav", "ground_truth_captions": "Water splashing followed by a woman speaking", "generated_captions": "There is the sound of water splashing and gurgling, as well as female speech throughout the entire duration of the audio."}
{"wav": "YoNHCc_izsDE.wav", "ground_truth_captions": "Water splashing and a baby laughing", "generated_captions": "There is laughter, water splashing and gurgling sounds throughout the audio."}
{"wav": "Y4pv3w--cRrA.wav", "ground_truth_captions": "An electric motor runs then a person speaks", "generated_captions": "There is the sound of an electric toothbrush and a man speaking throughout the entire duration of the audio."}
{"wav": "Y3ejndVEAcmQ.wav", "ground_truth_captions": "A cat meowing and hissing", "generated_captions": "The audio contains the sound of water flowing and splashing, along with mechanisms and generic impact sounds. Additionally, there is a cat meowing at the end."}
{"wav": "Y22L_3pBa1AI.wav", "ground_truth_captions": "A car is shifting gears", "generated_captions": "The audio contains the sound of an engine idling and accelerating, as well as generic impact sounds."}
{"wav": "YIdBDl9Wr51A.wav", "ground_truth_captions": "Synthesized laser effects and explosions as a man talks followed by a deeper voiced man talking then woman laughing", "generated_captions": "The audio contains music, male speech, and laughter."}
{"wav": "Y-FW109cbv0g.wav", "ground_truth_captions": "Speech and then a sneeze and laughter", "generated_captions": "There is a woman laughing, a dog whimpering and barking, and a man speaking."}
{"wav": "Y8DQfjqPCTI8.wav", "ground_truth_captions": "Swarm of bees buzzing and two men speaking", "generated_captions": "The audio contains the buzzing of bees and wasps, and a man speaking."}
{"wav": "YHdxfbpnd2-8.wav", "ground_truth_captions": "A man talking then whistling", "generated_captions": "The audio contains speech and breathing sounds."}
{"wav": "Yk1QxQ4jJaEQ.wav", "ground_truth_captions": "A man talking as an idle truck engine runs", "generated_captions": "There is the sound of an engine idling and a man speaking throughout the audio."}
{"wav": "YS8k47ME-YT4.wav", "ground_truth_captions": "Plastic cranking as rain heavily pours while a stream of water rapidly flows", "generated_captions": "The audio contains the sound of water running and splashing, as well as wind blowing into a microphone."}
{"wav": "YSNy_axSCoyw.wav", "ground_truth_captions": "Mechanical sound with clock tick-tocking", "generated_captions": "There is the ticking of a clock and mechanisms throughout the entire duration of the audio, along with the sound of crickets chirping from 10.68 to 9.75 seconds."}
{"wav": "Y3Sml1wHcuxo.wav", "ground_truth_captions": "A train horn goes off loudly", "generated_captions": "The audio contains the sound of a train horn blowing and a bell ringing."}
{"wav": "YG3YO2unWz7k.wav", "ground_truth_captions": "Sputtering of an idling and revving engine", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "Yram-QPKSQYc.wav", "ground_truth_captions": "Helicopter blades spinning then fading away", "generated_captions": "There is an engine idling throughout the entire duration of the audio, and there's also a brief moment where a squeal can be heard."}
{"wav": "YMOxddxW5PXs.wav", "ground_truth_captions": "Food and oil sizzling as a man is talking while metal clanks against a pan", "generated_captions": "The audio contains the sounds of frying food, dishes, pots and pans clanging, and male speech."}
{"wav": "Y8nUqSYC66mI.wav", "ground_truth_captions": "Several people cheer and scream and speak as water flows hard", "generated_captions": "There is speech noise throughout the entire duration of the audio, and there are sounds of children shouting and screaming from 4.61 to 9.03 seconds."}
{"wav": "Ye2rScj9UyMs.wav", "ground_truth_captions": "Pigeons cooing and bird wings flapping as footsteps shuffle on paper", "generated_captions": "The audio contains the sounds of birds cooing and flapping their wings, as well as generic impact sounds."}
{"wav": "YgkWd1HugK2w.wav", "ground_truth_captions": "Pigeons coo and flap their wings", "generated_captions": "The audio contains the sounds of birds cooing and flapping their wings, specifically pigeons."}
{"wav": "YDNtF_mGzQes.wav", "ground_truth_captions": "A crowd of children talking as a man speaks over an intercom as a large truck engine runs idle followed by pressurized air releasing", "generated_captions": "The audio contains sounds of people talking, children speaking, and background noise from vehicles."}
{"wav": "YEp72tyiL3as.wav", "ground_truth_captions": "Thunder crashes and echos", "generated_captions": "The audio contains the sounds of rain falling and thunder roaring, which indicate that it is raining heavily with thunderstorms."}
{"wav": "YpTJKJxaheI8.wav", "ground_truth_captions": "A man speaks with faint ticks of a clock", "generated_captions": "The audio contains background noise, breathing sounds, and speech by a male speaker."}
{"wav": "YSoO1HhaEc9Q.wav", "ground_truth_captions": "Rhythmic squeaking is ongoing, pigs oink, an adult male speaks, and music plays faintly in the background", "generated_captions": "The audio contains sounds of people talking, laughing, and birds chirping."}
{"wav": "YMvHpNzDpC6Q.wav", "ground_truth_captions": "Men riding in the car talking then man burps loudly and then the other chuckles", "generated_captions": "There is a man speaking, a pig oinking, and laughter."}
{"wav": "Yyau2WIRkxb8.wav", "ground_truth_captions": "A small high frequency motor vibrates", "generated_captions": "There is the sound of a power tool drilling throughout the entire clip, and there's also the sound of wood being sawed from 9.81 to 10 seconds."}
{"wav": "Y6ZwYgzcN6Is.wav", "ground_truth_captions": "A woman yelling and laughing as a group of people shout while ocean waves crash and wind blows into a microphone", "generated_captions": "The audio contains sounds of wind, waves, and surf, as well as male speech, laughter, and shouting."}
{"wav": "Y0On6-JiVwRs.wav", "ground_truth_captions": "Cat meowing sadly", "generated_captions": "There is a cat meowing and crying throughout the entire duration of the audio, from 0 to 10 seconds."}
{"wav": "Y3rna9zo5ZOs.wav", "ground_truth_captions": "A man is giving a speech and a crowd cheers", "generated_captions": "The audio contains sounds of cheering, shouting, and male speech."}
{"wav": "Y27HIamF8pKo.wav", "ground_truth_captions": "Railroad tracks clickety-clack as a train horn blasts", "generated_captions": "The audio contains the sounds of a train moving on tracks, wind blowing into a microphone, and a train horn being triggered."}
{"wav": "Yy-RSojxgkDo.wav", "ground_truth_captions": "A male speech and a bird chirping", "generated_captions": "The audio contains the sounds of birds chirping and tweeting, as well as a man speaking."}
{"wav": "Y_9mgOkzm-xg.wav", "ground_truth_captions": "A man speaks as food sizzles followed by some cracks", "generated_captions": "There is the sound of food sizzling and frying, along with male speech throughout the audio."}
{"wav": "Y1Og2TJ3bXW0.wav", "ground_truth_captions": "An aircraft engine humming followed by plastic clanking then an aircraft engine slowing down", "generated_captions": "The audio contains the sound of an aircraft engine running at idle, and there is also background noise throughout the clip."}
{"wav": "YWUpeplQr3A4.wav", "ground_truth_captions": "A man shrilling followed by a power tool drilling and a man screaming as liquid splatters", "generated_captions": "There is the sound of an engine revving and accelerating, a crowd cheering, and a child screaming."}
{"wav": "Yg_P29ucKj78.wav", "ground_truth_captions": "A race car accelerating and driving as plastic rattles", "generated_captions": "The audio contains sounds of motor vehicles, specifically motorcycles and cars accelerating and revving their engines."}
{"wav": "YQoEal_hKz4Q.wav", "ground_truth_captions": "Gunshots, machine gun fire, and artillery fire are ongoing, an adult male speaks in the foreground, and another adult male speaks in the far background", "generated_captions": "The audio contains the sound of machine gun firing and clicking noises."}
{"wav": "YBDpU2Qh77NE.wav", "ground_truth_captions": "A bird making vocalizations from a distance followed by several people whispering nearby", "generated_captions": "The audio contains bird vocalizations, wind noise, and the sound of birds flapping their wings."}
{"wav": "Y7RMpCCkQks0.wav", "ground_truth_captions": "An industrial motor is humming, and ripping and tearing are occurring", "generated_captions": "There is the sound of an aircraft engine running throughout the audio, and there's also the sound of wood being tapped towards the end."}
{"wav": "Y4eyY1w2QyM0.wav", "ground_truth_captions": "Ocean waves are hitting the shores", "generated_captions": "The audio contains the sounds of waves crashing and wind blowing into a microphone."}
{"wav": "YFi4-IqJo2xQ.wav", "ground_truth_captions": "Humming and rattling from a revving engine", "generated_captions": "The audio contains the sound of an engine idling and then revving up, which is characteristic of a lawn mower."}
{"wav": "YIKnx3hJv1bs.wav", "ground_truth_captions": "Bad quality audio", "generated_captions": "The audio contains music and the sound of an organ playing."}
{"wav": "Yr2KhpX_QgXA.wav", "ground_truth_captions": "A man speaks as a machine hums quietly and then increases in volume", "generated_captions": "There is a man speaking and the sound of an electric toothbrush running throughout the entire duration of the audio."}
{"wav": "YLP_DzNUkAKY.wav", "ground_truth_captions": "People speaking faintly with some humming and a hydraulic hiss", "generated_captions": "The audio contains mechanisms, speech babble, and generic impact sounds."}
{"wav": "Y7JWHbs3gu1w.wav", "ground_truth_captions": "A train roars and honks it horn", "generated_captions": "The audio contains sounds of a train horn blowing and a train moving on tracks."}
{"wav": "YBwnGxJD9xh8.wav", "ground_truth_captions": "Speech and a goat bleating", "generated_captions": "The audio contains sounds of children playing, birds chirping, and wind blowing."}
{"wav": "YiOCpICiu4LA.wav", "ground_truth_captions": "Insects buzzing and birds chirping as a man talks followed by a loud plastic popping", "generated_captions": "The audio contains sounds of birds chirping, insects buzzing, and a man speaking."}
{"wav": "YENTi8Sn4vdM.wav", "ground_truth_captions": "A river stream flowing while a woman and a kid are talking as birds chirp in the background", "generated_captions": "There is the sound of water running and splashing, as well as female speech throughout the duration of the audio."}
{"wav": "YPRUfwpmYwJ8.wav", "ground_truth_captions": "A man talking as compressed air is spraying with wood clanking in the distance", "generated_captions": "There is a man speaking and the sound of steam hissing throughout the audio."}
{"wav": "YObWjGBJF_94.wav", "ground_truth_captions": "Hissing and rattling", "generated_captions": "There is the sound of a power tool drilling and a mechanism working throughout the entire duration of the audio."}
{"wav": "YNtQiduPRiRg.wav", "ground_truth_captions": "A buzzing and laughter", "generated_captions": "There is the sound of an electric toothbrush, mechanisms, and a man speaking throughout the entire duration of the audio."}
{"wav": "Y8GHLfJ6y6zA.wav", "ground_truth_captions": "A man talking with keyboard typing and computer mouse clicking", "generated_captions": "The audio contains the sounds of typing on a computer keyboard, mechanisms, and a man speaking."}
{"wav": "Yn-JyOqYSLQM.wav", "ground_truth_captions": "Metal clanking followed by plastic rattling and air spraying with a group of people talking faintly in the background", "generated_captions": "There is the sound of dishes, pots, and pans clanging throughout the audio clip from 0 to 10 seconds."}
{"wav": "YmaVYiednkSg.wav", "ground_truth_captions": "A man speaks with spraying and vibration in the background", "generated_captions": "There is a continuous mechanism sound throughout the entire duration of the audio, and there is also speech occurring from 1 minute and 25 seconds to approximately 3 minutes and 40 seconds."}
{"wav": "YZUmZgPL0ges.wav", "ground_truth_captions": "Multiple large bells are madly ringing", "generated_captions": "The audio contains the sound of change ringing, which is a method of ringing a set of tuned bells in a controlled way."}
{"wav": "YMSziND26UTA.wav", "ground_truth_captions": "Insects buzzing while wind is blowing on a microphone as music faintly plays followed by a rooster crowing", "generated_captions": "The audio contains sounds of insects buzzing, wind blowing into the microphone, and distant bird chirping."}
{"wav": "YDrCm-HpX67k.wav", "ground_truth_captions": "Opening and closing followed by tapping", "generated_captions": "The audio contains the sounds of typing on a computer keyboard and mechanisms."}
{"wav": "YEUZaxaWqhwg.wav", "ground_truth_captions": "A slap occurs and an aircraft engine runs as a man and child talk", "generated_captions": "The audio contains sounds of water splashing, wind blowing into the microphone, and people speaking."}
{"wav": "YhqPBcvex1VU.wav", "ground_truth_captions": "An infant crying as a woman mumbles", "generated_captions": "There is a baby crying and breathing sounds throughout the audio, with some background noise."}
{"wav": "Yj_NSuPnx5LA.wav", "ground_truth_captions": "Dialing phone followed by clack sound", "generated_captions": "The audio contains the sounds of typing on a computer keyboard and mechanisms."}
{"wav": "YEfk5kdn9lR8.wav", "ground_truth_captions": "Child talking then door crashing and her screaming", "generated_captions": "There is a child speaking, a woman speaking, and mechanisms sounds throughout the audio."}
{"wav": "YfPqj3nnwQOI.wav", "ground_truth_captions": "Ocean waves crashing and water trickling", "generated_captions": "The audio contains the sound of waves crashing and wind blowing into a microphone."}
{"wav": "YZTYAQBnU4GM.wav", "ground_truth_captions": "Pet birds tweet, chirp, and sing while music plays", "generated_captions": "The audio contains bird chirping and tweeting sounds, along with the sound of wind blowing into a microphone."}
{"wav": "YFc9pG54DDJM.wav", "ground_truth_captions": "A toilet flushing followed by paper crinkling and a door slamming in the distance", "generated_captions": "There is the sound of water flushing down a toilet and then filling up again, along with some generic impact sounds."}
{"wav": "YpHNMcX-9FDs.wav", "ground_truth_captions": "A dog whimpering constantly then ultimately growls", "generated_captions": "The audio contains sounds of dogs barking and howling, as well as background noise throughout the entire clip."}
{"wav": "YR91bUbtKrRs.wav", "ground_truth_captions": "Two women are talking, and a baby cries", "generated_captions": "There is a woman speaking, a baby crying, and mechanisms sounds throughout the audio."}
{"wav": "Ym8wV38lf2jg.wav", "ground_truth_captions": "Emergency sirens and muffled speech", "generated_captions": "The audio contains the sound of an emergency vehicle siren, specifically a police car siren, and generic impact sounds."}
{"wav": "YcNARVD02-tw.wav", "ground_truth_captions": "A man and an elderly woman talking as plastic clacks followed by a faucet pouring water as water runs down a drain", "generated_captions": "There is the sound of water running and a woman speaking throughout the audio."}
{"wav": "Yq1ivQ_2fddk.wav", "ground_truth_captions": "Constant hissing with mean having conversation", "generated_captions": "There is a continuous hissing noise throughout the audio, and there is also speech by a male speaker."}
{"wav": "YqakN0JNbpcU.wav", "ground_truth_captions": "A man is speaking and a fly is buzzing around", "generated_captions": "The audio contains sounds of mechanisms, breathing, and generic impact sounds."}
{"wav": "YWLzzpzOKtnY.wav", "ground_truth_captions": "Male speech and an insect buzzing", "generated_captions": "The audio contains speech and the sound of rain falling on a surface."}
{"wav": "Y4YMXgLFcR94.wav", "ground_truth_captions": "A man speaks and then an audience claps", "generated_captions": "The audio contains sounds of male speech, applause, and breathing."}
{"wav": "YHdPSebdDxe4.wav", "ground_truth_captions": "A male speaking and then growling followed by more male speaking", "generated_captions": "There is music playing throughout the entire duration of the audio, and there are also sounds of speech synthesizer and human voice."}
{"wav": "Y_z6pymOet7g.wav", "ground_truth_captions": "A man talking followed by a toilet flushing", "generated_captions": "There is a man speaking, water pouring into a sink, and the sound of flushing a toilet."}
{"wav": "YnmLMLgWPmFM.wav", "ground_truth_captions": "A motorboat engine running as water splashes and a man shouts followed by birds chirping in the background", "generated_captions": "There is the sound of water splashing and gurgling throughout the entire duration of the audio, along with wind blowing into a microphone from 9.75 to 10 seconds."}
{"wav": "YtB8TiiXwKmA.wav", "ground_truth_captions": "A drill running", "generated_captions": "There is the sound of a helicopter engine running throughout the entire clip, and there's also the sound of wood being sawed from 10.0 to 10.0 seconds."}
{"wav": "YpHYkWkZ4guE.wav", "ground_truth_captions": "Scraping and hissing with some light knocks", "generated_captions": "There is the sound of wood being rubbed and tapped throughout the entire duration of the audio, from start to finish."}
{"wav": "Ygbi6MxPf3hA.wav", "ground_truth_captions": "Winds and ocean waves crashing while a chime instrument briefly plays a melody", "generated_captions": "The audio contains the sounds of waves, wind blowing into a microphone, and children speaking."}
{"wav": "YtdpiXW68adA.wav", "ground_truth_captions": "A woman sobbing and speaking", "generated_captions": "There is crying, breathing sounds, and laughter in the audio."}
{"wav": "Yi6MQCm58zlY.wav", "ground_truth_captions": "A critter squealing as a man is talking and leaves are rustling", "generated_captions": "The audio contains sounds of mechanisms, wind, birds chirping and tweeting, and a man speaking."}
{"wav": "YMkbP_8zJwXU.wav", "ground_truth_captions": "A bird chirping as water lightly trickles and wind blows into a microphone", "generated_captions": "The audio contains bird vocalizations, wind noise, and the sound of water flowing."}
{"wav": "YBrPFQDr99Gg.wav", "ground_truth_captions": "A crowd cheers and a man speaks", "generated_captions": "The audio contains sounds of cheering, shouting, and clapping from a crowd, as well as male speech."}
{"wav": "YcK2kSVR1d2o.wav", "ground_truth_captions": "Popping and cracking followed by a loud burst", "generated_captions": "The audio contains video game sounds, gunfire, and machine gun fire."}
{"wav": "Y8ZH_PoK0clI.wav", "ground_truth_captions": "Footsteps then a woman speaks followed by a door clanging", "generated_captions": "The audio contains sounds of mechanisms, generic impact sounds, and surface contact, as well as male speech."}
{"wav": "Yy_OyLW9lBXU.wav", "ground_truth_captions": "A baby cries and people speak", "generated_captions": "There is a baby crying and babbling, along with some background noise throughout the entire duration of the audio."}
{"wav": "Yp9qRTh4BmSE.wav", "ground_truth_captions": "Adult males shout in the distance and an adult male shout close by, two adult males speak in the foreground, and gunfire erupts", "generated_captions": "There is a man speaking, birds chirping and singing, gunshots, and background noise throughout the audio."}
{"wav": "Y3qTL7QRk-tg.wav", "ground_truth_captions": "Water running together with distant singing and brief clanking", "generated_captions": "The audio contains the sound of water running and splashing, along with mechanisms operating."}
{"wav": "Ysl_Pxpc7beo.wav", "ground_truth_captions": "A vehicle is honking the horn", "generated_captions": "The audio contains the sound of an engine running, wind blowing into a microphone, and a musical horn playing."}
{"wav": "YB3O476LeuXY.wav", "ground_truth_captions": "An idle motorbike engine running", "generated_captions": "The audio contains the sound of an engine idling, specifically from a medium-sized vehicle."}
{"wav": "YG0IsabU5hn4.wav", "ground_truth_captions": "Wind blowing heavily into a microphone as ocean waves crash and leaves rustle", "generated_captions": "The audio contains the sounds of wind blowing and waves crashing."}
{"wav": "Yw_Utn3CwAXE.wav", "ground_truth_captions": "A toilet flushes followed by a metal latch clanking then a door slowly creaking open", "generated_captions": "There is the sound of water running and splashing, along with generic impact sounds throughout the duration of the audio."}
{"wav": "YrvtA7c1I4xo.wav", "ground_truth_captions": "Whooshing of wind followed by a man speaking with sneakers squeaking on hardwood", "generated_captions": "There is wind noise, mechanisms, and generic impact sounds throughout the audio. Additionally, there are male speech segments from 0:58 to 1:24 and from 3:96 to 4:72."}
{"wav": "YI_8KqxP5xOA.wav", "ground_truth_captions": "A sprayer is spraying surfaces", "generated_captions": "There is the sound of steam hissing throughout the audio, and there's also the sound of a train engine running on railroad tracks."}
{"wav": "Yorgwzt45ojE.wav", "ground_truth_captions": "A man speaks as pigeons coo and wings flap", "generated_captions": "The audio contains the sounds of pigeons cooing, birds chirping, and people conversing."}
{"wav": "YtwFypUcdgRc.wav", "ground_truth_captions": "A man yelling as another man is laughing as wind blows heavily into a microphone", "generated_captions": "The audio contains sounds of wind, laughter, speech, and a rooster crowing."}
{"wav": "Y6pssFJ0m-kU.wav", "ground_truth_captions": "Leaves rustle in the wind as small birds chirp", "generated_captions": "The audio contains wind noise, rustling leaves, and birds chirping."}
{"wav": "Y54eRRbCtPn8.wav", "ground_truth_captions": "An adult female speaks in a quiet environment", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "Yp_BB_rJaF7Q.wav", "ground_truth_captions": "Male speaking softly with nature sounds in background", "generated_captions": "The audio contains the sounds of birds chirping and singing, as well as the presence of insects."}
{"wav": "Y350OCezayrk.wav", "ground_truth_captions": "An engine being turned over and then started", "generated_captions": "The audio contains the sound of an engine starting and idling, along with mechanisms sounds throughout its duration."}
{"wav": "YK8-b0VtNOqA.wav", "ground_truth_captions": "Horses snorting then neighing as footsteps shuffle and people talk in the background", "generated_captions": "There is a horse neighing, people talking and laughing, and background music playing throughout the audio."}
{"wav": "Y8ycflE3dIHw.wav", "ground_truth_captions": "Train passing followed by short honk", "generated_captions": "The audio contains the sound of a train horn blowing and a train passing by."}
{"wav": "YBUAPM4D3-h8.wav", "ground_truth_captions": "Women, child talking and birds chirping", "generated_captions": "The audio contains bird vocalizations, chirping and tweeting sounds throughout the entire duration of the clip from 0 to 10 seconds."}
{"wav": "Y1IoHRTUp86c.wav", "ground_truth_captions": "An aircraft engine humming as a woman speaks over an intercom followed by an aircraft engine accelerating", "generated_captions": "The audio contains the sound of an aircraft engine idling, which is described as a propeller plane."}
{"wav": "YXQxIXaX_7M0.wav", "ground_truth_captions": "Water rushing loudly while a man yells in the background", "generated_captions": "There is the sound of water flowing and splashing, along with male speech."}
{"wav": "Y4ftDFi4684Y.wav", "ground_truth_captions": "Several slight bangs occur during a constant ticktock", "generated_captions": "The audio contains the sounds of mechanisms, tapping, and generic impact sounds."}
{"wav": "YeYbFtxZmKL4.wav", "ground_truth_captions": "Clanking and rustling with people faintly speaking and horse clip-clopping in the background", "generated_captions": "The audio contains the sounds of pigeons cooing, birds chirping, and people talking."}
{"wav": "Yv59uHr-B1no.wav", "ground_truth_captions": "Frogs and crickets chirping during nature ambiance", "generated_captions": "The audio contains the sounds of frogs croaking and insects chirping."}
{"wav": "YBz9Y5nZK3eo.wav", "ground_truth_captions": "Typing on a keyboard", "generated_captions": "The audio contains the sound of typing on a computer keyboard."}
{"wav": "Yc6YJgZ3qzOw.wav", "ground_truth_captions": "A toy helicopter flying followed by wind blowing into a microphone", "generated_captions": "The audio contains the sound of an engine idling and revving, specifically from a medium-sized vehicle or motorcycle."}
{"wav": "Y3hzy-FL24no.wav", "ground_truth_captions": "A stream of water flowing and trickling as a small motor hum in the background followed by camera muffling", "generated_captions": "The audio contains the sound of water flowing and splashing, along with mechanisms."}
{"wav": "YwbPmnxCLoRQ.wav", "ground_truth_captions": "Several bells ringing rapidly and then a single bell", "generated_captions": "The audio contains the sound of church bells ringing, specifically change ringing."}
{"wav": "Ys_EWjoiVfzo.wav", "ground_truth_captions": "A sewing machine operating several times followed by metal clanking", "generated_captions": "The audio contains the sound of a sewing machine running and mechanisms working throughout its duration."}
{"wav": "YmSF_FqBtRPs.wav", "ground_truth_captions": "A telephone ringing with loud echo", "generated_captions": "There is an alarm clock ringing throughout the entire duration of the audio, and there's also background noise present from start to finish."}
{"wav": "Y5OM3tJh51pE.wav", "ground_truth_captions": "A lady speaking", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "Y_BSmz3SEW1w.wav", "ground_truth_captions": "Pigeons coo and rustle", "generated_captions": "The audio contains the sounds of birds cooing and flapping their wings, as well as generic impact sounds."}
{"wav": "YOt0bN_hz2ec.wav", "ground_truth_captions": "A train horn honks with a train racing by", "generated_captions": "The audio contains the sound of a train horn blowing and a train passing by."}
{"wav": "YHkbCUN4V3TU.wav", "ground_truth_captions": "A girl screams and people speak", "generated_captions": "There is screaming, crying, and breathing sounds throughout the audio."}
{"wav": "YTSdAJWJ-tW0.wav", "ground_truth_captions": "Two vehicles drive by as a man is speaking in the distance", "generated_captions": "The audio contains sounds of mechanisms, specifically an engine running and accelerating, as well as male speech."}
{"wav": "Y4sb9jN0SgTM.wav", "ground_truth_captions": "A motor vehicle engine runs and revs, then it stops and an adult male speaks", "generated_captions": "The audio contains the sound of a race car accelerating and skidding, as well as male speech."}
{"wav": "YDjKGzOe_COc.wav", "ground_truth_captions": "A woman is performing a speech", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YMtK8L8gXRrI.wav", "ground_truth_captions": "A toilet is flushing followed by a cat meowing", "generated_captions": "There is the sound of water flushing down a toilet and trickling, along with generic impact sounds throughout the audio."}
{"wav": "Y1FNJbN-eHY4.wav", "ground_truth_captions": "Burping and girls laughing with many voices in the background", "generated_captions": "There is a sound of burping, laughter, and speech throughout the audio."}
{"wav": "YtNxfdAd14qE.wav", "ground_truth_captions": "Mechanical rotation and then a loud click occurs", "generated_captions": "The audio contains the sound of water flowing and splashing, along with generic impact sounds."}
{"wav": "YlgwpIImXCWA.wav", "ground_truth_captions": "A man briefly speaks followed by a sawing sound, and then starts talking again", "generated_captions": "There is a sound of a drill being used throughout the entire duration of the audio, and there is also speech by multiple male speakers."}
{"wav": "YXi6V0LGvqoo.wav", "ground_truth_captions": "A dog barking followed by a dog growling as footsteps squeak on a hard surface floor and followed by series of metal clicks", "generated_captions": "There is a dog barking and growling throughout the audio, with background noise of mechanisms."}
{"wav": "YK-7Y8yhcUiw.wav", "ground_truth_captions": "An animal snores", "generated_captions": "There is a dog growling and snorting throughout the entire duration of the audio, with background noise also present from start to finish."}
{"wav": "Y0AsXkZkqelg.wav", "ground_truth_captions": "A loud bang followed by an engine idling loudly", "generated_captions": "The audio contains the sound of an engine idling and revving up, which is likely from a lawn mower or similar device."}
{"wav": "Y6ukYSXzfEgQ.wav", "ground_truth_captions": "Metal clacking followed by water flowing and splashing into a container then draining down a pipe", "generated_captions": "The audio contains the sound of water running from a faucet and splashing into a sink, along with generic impact sounds."}
{"wav": "YBoe3MeEpn_c.wav", "ground_truth_captions": "A man speaking, with the clinking of dishes in the background, following by the hiss of an oil mister spraying", "generated_captions": "There is a continuous hissing noise throughout the audio, and there are also sounds of mechanisms and male speech."}
{"wav": "Y1WTSW96XP6E.wav", "ground_truth_captions": "A man speaks followed by several clicks then an engine struggling to start", "generated_captions": "The audio contains sounds of mechanisms, fire, and generic impact sounds."}
{"wav": "YAI1OweEW8C0.wav", "ground_truth_captions": "Light rain and water dripping followed by thunder", "generated_captions": "The audio contains the sounds of rain falling and thunder roaring."}
{"wav": "YcFoXRmGgIME.wav", "ground_truth_captions": "A train horn honking as a train is running on a railroad track and wind is blowing into a microphone", "generated_captions": "The audio contains the sound of a train horn blowing and a train passing by."}
{"wav": "Y4CAMv5nlr-0.wav", "ground_truth_captions": "A man speaking followed by a crowd of people applauding and cheering", "generated_captions": "The audio contains sounds of male speech, crowd cheering and applause."}
{"wav": "YcN-oYKd-M4E.wav", "ground_truth_captions": "Sheep baaing followed by plastic thumping as birds chirp in the distance", "generated_captions": "The audio contains sounds of birds, insects, and animals."}
{"wav": "YHg6HxylRGDo.wav", "ground_truth_captions": "Emergency sirens wailing", "generated_captions": "There is an emergency vehicle siren and a car passing by in the background throughout the entire duration of the audio."}
{"wav": "YggN4-K5AgoM.wav", "ground_truth_captions": "A toilet flushing", "generated_captions": "The audio contains the sound of water running from a faucet and splashing into a sink, along with generic impact sounds."}
{"wav": "YV8A0VRGdgwM.wav", "ground_truth_captions": "Pebbles and rocks bouncing off of a wooden surface as footsteps walk on gravel and dirt followed by a goat baaing as a muffled animal moan in the background", "generated_captions": "The audio contains sounds of footsteps, generic impact sounds, and surface contact noises."}
{"wav": "YxnVqvc7N7Po.wav", "ground_truth_captions": "A woman and man speaking followed by a phone clicking then a phone call ring", "generated_captions": "The audio contains speech, breathing sounds, and background noise."}
{"wav": "Y2KEfkDO6hlA.wav", "ground_truth_captions": "Vehicle accelerating", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with generic impact sounds."}
{"wav": "Yt3VFlDiEKgY.wav", "ground_truth_captions": "An insect buzzing followed by a man talking", "generated_captions": "There is the buzzing of insects throughout, and there's also a brief moment where someone speaks."}
{"wav": "Y-mhFGevxLUg.wav", "ground_truth_captions": "Male speaking with another male voice in the background", "generated_captions": "The audio contains speech by multiple speakers, specifically male speech."}
{"wav": "YmW1EpJYcy_E.wav", "ground_truth_captions": "A motorbike accelerating and revving as wind blows into a microphone", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with generic impact sounds."}
{"wav": "YR8bHTHnF8j4.wav", "ground_truth_captions": "A helicopter engine running idle", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "YDAN1t9ukkg0.wav", "ground_truth_captions": "A person is typing keyboard with some mouse clicking", "generated_captions": "The audio contains the sound of typing on a computer keyboard throughout its duration, from 0:00 to 10:00."}
{"wav": "YJHhEjsAkZoc.wav", "ground_truth_captions": "A train is passing by and sound its whistle.", "generated_captions": "The audio contains the sound of a train horn blowing and a train passing by."}
{"wav": "Y9PN4gyxpH2M.wav", "ground_truth_captions": "A man and a woman talking then the crinkling of paper", "generated_captions": "The audio contains sounds of crumpling and crinkling, mechanisms, and male speech."}
{"wav": "Y7bO0AJI-ihs.wav", "ground_truth_captions": "Horses trotting on a hard surface as a motor rumbles rapidly for a brief period in the background", "generated_captions": "The audio contains the sounds of wind blowing and a horse trotting."}
{"wav": "Y4bUL_ttiOdw.wav", "ground_truth_captions": "A baby is crying", "generated_captions": "There is a baby crying and breathing sounds throughout the audio, along with some generic impact sounds."}
{"wav": "YLF6x7B0Ppvo.wav", "ground_truth_captions": "A racing car is driving fast", "generated_captions": "The audio contains the sound of a race car accelerating and skidding, along with background music."}
{"wav": "Yz1ax0QPpd14.wav", "ground_truth_captions": "A large duck quacks and small ducks chirp", "generated_captions": "The audio contains sounds of ducks quacking, wind blowing into the microphone, and water splashing."}
{"wav": "YUjje3lSabsg.wav", "ground_truth_captions": "Soft, rapid snoring is ongoing, and faint speech occurs in the background", "generated_captions": "There is snoring, breathing sounds, and mechanisms throughout the entire duration of the audio."}
{"wav": "Y5K1mISHwggI.wav", "ground_truth_captions": "A man speaks with others speaking in the distance and traffic passing with a few horns honking", "generated_captions": "The audio contains speech, generic impact sounds, and background noise."}
{"wav": "YJdFmMw0zyKA.wav", "ground_truth_captions": "A kid speaking followed by a seal making noises then water splashing as a kid and woman are laughing", "generated_captions": "There is splashing water, laughter, and speech throughout the audio."}
{"wav": "YD96OO7nYYsg.wav", "ground_truth_captions": "A vehicle accelerating then revving", "generated_captions": "The audio contains the sound of an engine accelerating and revving, along with tire squealing."}
{"wav": "YvaujJ7msKfc.wav", "ground_truth_captions": "Wind blowing with distant traffic passing and sirens ringing", "generated_captions": "The audio contains sounds of traffic, motor vehicles (road), and an engine accelerating or revving up."}
{"wav": "YlrKGCtSsAkA.wav", "ground_truth_captions": "A toy helicopter engine flying as wind blows into a microphone", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "YEY4p0_NJVQs.wav", "ground_truth_captions": "A woman is performing a speech", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "YxqtrbqDlz28.wav", "ground_truth_captions": "A sneeze occurs followed by sniffling and the start of another sneeze, while a baby coos in the background", "generated_captions": "There is a baby laughing and babbling, along with snoring sounds throughout the audio."}
{"wav": "Yc3nlaAkv9bA.wav", "ground_truth_captions": "A male voice talking and the bleat of a goat", "generated_captions": "There is a dog barking, and there are sounds of mechanisms throughout the audio."}
{"wav": "Y9_YfTz8cnFY.wav", "ground_truth_captions": "Steam hissing followed by a train whistle blowing and a group of people talking in the background", "generated_captions": "The audio contains the sound of an aircraft engine running and accelerating, along with wind blowing into a microphone."}
{"wav": "Y--0w1YA1Hm4.wav", "ground_truth_captions": "High pitched speaking and laughing", "generated_captions": "There is a woman speaking, laughter, breathing sounds, and mechanisms throughout the audio."}
{"wav": "Y1vCYiVvZ7VE.wav", "ground_truth_captions": "A woman speeches", "generated_captions": "The audio contains speech, breathing sounds, and the sound of water running."}
{"wav": "YAf4a-9rcnP0.wav", "ground_truth_captions": "Bursting and popping noises like gunfire", "generated_captions": "The audio contains the sounds of gunshots and artillery fire, as well as wind blowing into a microphone."}
{"wav": "Yjj2RyNDj7no.wav", "ground_truth_captions": "Birds chirping as insects buzzing followed by a man talking in the distance", "generated_captions": "The audio contains sounds of birds chirping, insects buzzing, and a camera clicking."}
{"wav": "Y6dLkgq9EKPE.wav", "ground_truth_captions": "A man speaks with some faint clicks and humming", "generated_captions": "The audio contains speech and breathing sounds."}
{"wav": "YGGgQR7aIofY.wav", "ground_truth_captions": "A horn beeps a tune, and a large motor vehicle engine is running and gets louder", "generated_captions": "The audio contains the sound of a train horn blowing and a train passing by."}
{"wav": "YS0SQyFXbqF8.wav", "ground_truth_captions": "A child talking then laughing with a man as an animal gurgles", "generated_captions": "There is a baby laughing, a woman speaking, and water splashing sounds throughout the audio."}
{"wav": "YbLZFtoWXYTA.wav", "ground_truth_captions": "A cup is filled from a faucet", "generated_captions": "There is the sound of water running from a faucet and splashing into a sink throughout the entire duration of the audio, as well as background noise."}
{"wav": "YndxkSQKxaak.wav", "ground_truth_captions": "A motorcycle engine is running while a man is talking", "generated_captions": "There is the sound of an engine idling and accelerating, as well as male speech throughout the audio."}
{"wav": "Yii3Geza3hAU.wav", "ground_truth_captions": "Vibrations from a sewing machine", "generated_captions": "The audio contains the sound of an engine idling and knocking, which is commonly associated with a car engine running at idle speed."}
{"wav": "YniwgMbB6tpQ.wav", "ground_truth_captions": "Plastic clicking and clacking followed by a woman snoring", "generated_captions": "There is snoring, tapping and mechanisms sounds throughout the audio."}
{"wav": "YAUJPx81qKtY.wav", "ground_truth_captions": "A man talks and insects buzz", "generated_captions": "There is speech by multiple speakers, mechanisms, and the sound of insects buzzing throughout the audio."}
{"wav": "Y6i5eQOpFk_U.wav", "ground_truth_captions": "Water flowing from a faucet with some light bangs and a man speaking", "generated_captions": "There is the sound of water running from a faucet, and a man speaking throughout the duration of the audio."}
{"wav": "YXWw7ZM1c_QA.wav", "ground_truth_captions": "Wood sanding followed by a woman talking as a clock ticks proceeded by a cuckoo clock alarm cooing and bell ringing", "generated_captions": "The audio contains mechanisms, generic impact sounds, and surface contact sounds throughout the entire duration of the recording. Additionally, there is a cat meowing at intervals (0:14-0:23), (0:56-1:07), (1:19-1:28), (1:37-1:46), (1:55-2:04), (2:13-2:22), (2:31-2:40), (2:49-2:58), (3:07-3:16), (3:25-3:34), (3:43-3:52), (4:01-4:10), (4:19-4:28), (4:37-4:46), (4:55-5:04), (5:13-5:22), (5:31-5:40), (5:49-5:58), (6:07-6:16), (6:25-6:34), (6:43-6:52), (7:01-7:10), (7:19-7:28), (7:37-7:46), (7:55-8:04), (8:13-8:22), (8:31-8:40), (8:49-8:58), (9:07-9:16), (9:25-9:34), (9:43-9:52)."}
{"wav": "YSQHYl2Kp5ww.wav", "ground_truth_captions": "Music plays while two men speak each other with dishes clanking and food sizzling", "generated_captions": "There is speech, music, and the sound of frying food throughout the audio."}
{"wav": "Y4UPOUGVMlEs.wav", "ground_truth_captions": "Snorting and breathing", "generated_captions": "There is a sound of someone breathing heavily and snoring throughout the entire duration of the audio, along with background noise."}
{"wav": "Yo3mZR8OvPko.wav", "ground_truth_captions": "A racing vehicle accelerating and revving while tires skid and squeal", "generated_captions": "The audio contains the sound of a race car accelerating and revving its engine, along with background noise."}
{"wav": "YMVGhC-xB79s.wav", "ground_truth_captions": "Whistling is ongoing, a child speaks and an adult male speaks, birds coo, and rustling and soft metal clattering are occurring", "generated_captions": "There is whistling, bird vocalization, and human voice sounds throughout the audio."}
{"wav": "YQ0anPAIkfBE.wav", "ground_truth_captions": "A baby sobs and then a woman speaks followed a woman laughing", "generated_captions": "The audio contains sounds of crying, babbling, and breathing."}
{"wav": "YeqcdsdLz954.wav", "ground_truth_captions": "A synthesized whooshing followed by an explosion and fire crackling while gusts of wind blow", "generated_captions": "The audio contains the sounds of rain falling and thunder clapping, as well as an explosion."}
{"wav": "YQTSKjweEWew.wav", "ground_truth_captions": "Wind blowing followed by a man speaking", "generated_captions": "The audio contains wind noise and the sound of waves crashing against rocks."}
{"wav": "YrINmxSXMR-s.wav", "ground_truth_captions": "A duck quacks and splashes and a human chuckles", "generated_captions": "The audio contains sounds of ducks quacking, water splashing and gurgling, wind blowing into the microphone, and laughter."}
{"wav": "YmGa2JgAiKV8.wav", "ground_truth_captions": "Young man speaking with slight movement sounds", "generated_captions": "The audio contains speech, laughter, and breathing sounds."}
{"wav": "YkLYCjD6vWI4.wav", "ground_truth_captions": "Hissing of a steam engine train", "generated_captions": "There is the sound of a power tool drilling and wood being sawed throughout the entire duration of the audio, from start to finish."}
{"wav": "YCwxgQS3SXic.wav", "ground_truth_captions": "Vibrations from a sewing machine", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "YE9zN3-C64KE.wav", "ground_truth_captions": "Scratching noises accompanied by a female voice", "generated_captions": "There is the sound of something being rubbed against another hard object throughout the entire duration of the audio, and there is also background noise."}
{"wav": "Y8o-Y4QP8LWs.wav", "ground_truth_captions": "Some clanking and banging and a man speaking", "generated_captions": "There is speech, mechanisms, and generic impact sounds throughout the audio."}
{"wav": "YOFVzrakJhbw.wav", "ground_truth_captions": "A woman laughing followed by the bleating of sheep and a soft breeze", "generated_captions": "The audio contains sounds of water splashing, ducks quacking, and people talking."}
{"wav": "YTWOgvDaDqlU.wav", "ground_truth_captions": "A power tool drilling followed by a large motor running as wood is being sawed", "generated_captions": "There is the sound of a small motor running throughout the entire clip, and there's also the sound of wood being sawed from 10 seconds into the recording until its end at 10 seconds."}
{"wav": "YBQ-r9mEHssU.wav", "ground_truth_captions": "A woman laughs and talk as a hose clip-clops", "generated_captions": "There is speech, laughter, and water splashing sounds throughout the audio."}
{"wav": "Y7upINC4seBw.wav", "ground_truth_captions": "A man talking as an idle motorboat engine runs and water trickles while wind is blowing into a microphone", "generated_captions": "There is the sound of an engine idling throughout the audio, and there's also speech from male speakers."}
{"wav": "YETb9EIQOMAA.wav", "ground_truth_captions": "A female speaking", "generated_captions": "The audio contains speech and breathing sounds, with the woman speaking English."}
{"wav": "YF-47fRplQEc.wav", "ground_truth_captions": "Different female voices speaking followed by sheep bleating from a distance and voices of young people shortly thereafter", "generated_captions": "There is speech, laughter, and bird vocalization sounds throughout the audio."}
{"wav": "Yo7jW6Suyfbs.wav", "ground_truth_captions": "A man talks in the distance followed by several vehicles driving and accelerating", "generated_captions": "The audio contains sounds of motor vehicles, specifically cars and trucks, as well as male speech."}
{"wav": "Ylq9RvAA4mqY.wav", "ground_truth_captions": "A man talking then clearing his throat as food sizzles and a metal pot clangs", "generated_captions": "There is the sound of water running and gurgling, along with male speech throughout the duration of the audio."}
{"wav": "Y9z8XIRyUq9Q.wav", "ground_truth_captions": "A woman speaking", "generated_captions": "The audio contains speech by a female speaker, and background noise throughout the entire duration of the recording."}
{"wav": "Y7P0N61TVOxE.wav", "ground_truth_captions": "A band plays horn and string instruments while waves crash nearby", "generated_captions": "The audio contains music, specifically brass instruments playing a melody with a tuba and trombone."}
{"wav": "Y2ABngPM3raQ.wav", "ground_truth_captions": "A man talking as music is playing followed by a frog croaking", "generated_captions": "The audio contains music, speech synthesizer sounds, and male singing."}
{"wav": "YJhGp7HmRQxg.wav", "ground_truth_captions": "A metal clack followed by a horse neighing as gusts of wind blow and birds chirp in the background", "generated_captions": "The audio contains wind noise, bird vocalizations, and generic impact sounds."}
{"wav": "YPWjEfOkb6ro.wav", "ground_truth_captions": "Water running with distant speech in the background", "generated_captions": "There is the sound of water flowing and splashing, as well as male speech throughout the duration of the audio."}
{"wav": "YgW7s3YAthpI.wav", "ground_truth_captions": "A person gulping followed by glass tapping then liquid shaking in a container proceeded by liquid pouring before plastic thumps on paper", "generated_captions": "There is the sound of water splashing and trickling throughout the entire duration of the audio, along with some background noise."}
{"wav": "Y77nElZGi5NU.wav", "ground_truth_captions": "Wind blowing hard with a loud explosion and people laughing", "generated_captions": "The audio contains the sounds of wind blowing and rain falling, along with generic impact sounds."}
{"wav": "YJmWaRt8-u0s.wav", "ground_truth_captions": "A motorcycle engine running idle while two men communicate with each other", "generated_captions": "There is an engine idling throughout the audio, and there are sounds of male speech at intervals (0.13-0.42, 1.58-1.97, 2.68-3.09, 3.98-4.38, 5.08-5.49, 6.27-6.68, 7.48-7.89, 8.69-9.10)."}
{"wav": "Y-JP1GqPEKtw.wav", "ground_truth_captions": "A man talking as a power tool motor runs followed by the buzzing of an electric sanding machine", "generated_captions": "There is a man speaking and the sound of an electric toothbrush running throughout the audio."}
{"wav": "YoN0IcZaHD_8.wav", "ground_truth_captions": "A man speaks followed by a tools drilling wood", "generated_captions": "There is a man speaking, mechanisms running, and steam hissing sounds throughout the audio."}
{"wav": "Y30D1tqNFHMc.wav", "ground_truth_captions": "A loud white noise and then some beeping", "generated_captions": "There is the sound of water flowing and splashing, along with mechanisms running throughout the entire duration of the audio clip from 0 to 10 seconds."}
{"wav": "Y-Sz4z0QwEuM.wav", "ground_truth_captions": "A long, loud burp", "generated_captions": "There is a burping sound and breathing sounds throughout the audio."}
{"wav": "YeXj9OAik5cc.wav", "ground_truth_captions": "An idle motorbike engine running as a bird chirps in the background and wind blows into a microphone", "generated_captions": "The audio contains the sound of an engine idling, specifically a medium frequency engine."}
{"wav": "YbhlhcGONisM.wav", "ground_truth_captions": "A man speaks followed by thumps and clicks with some faint grunts", "generated_captions": "The audio contains sounds of mechanisms, ticks, and breathing."}
{"wav": "YJsoBpL86R5U.wav", "ground_truth_captions": "A woman talking then a child talking followed by a man talking then a goat yelling", "generated_captions": "The audio contains sounds of mechanisms, wind, and children speaking."}