Error while trying to transcript

[shahidirfan100]

C:\Users\Shahid\Desktop\Python Scripts\whisper-main\whisper\transcribe.py:79: UserWarning: FP16 is not supported on CPU; using FP32 instead
warnings.warn("FP16 is not supported on CPU; using FP32 instead")
Traceback (most recent call last):
File "C:\Users\Shahid\Desktop\Python Scripts\whisper-main\main.py", line 4, in
result = model.transcribe("audio.mp3")
File "C:\Users\Shahid\Desktop\Python Scripts\whisper-main\whisper\transcribe.py", line 85, in transcribe
mel = log_mel_spectrogram(audio)
File "C:\Users\Shahid\Desktop\Python Scripts\whisper-main\whisper\audio.py", line 111, in log_mel_spectrogram
audio = load_audio(audio)
File "C:\Users\Shahid\Desktop\Python Scripts\whisper-main\whisper\audio.py", line 42, in load_audio
ffmpeg.input(file, threads=0)
File "C:\Users\Shahid\AppData\Local\Programs\Python\Python310\lib\site-packages\ffmpeg_run.py", line 313, in run
process = run_async(
File "C:\Users\Shahid\AppData\Local\Programs\Python\Python310\lib\site-packages\ffmpeg_run.py", line 284, in run_async
return subprocess.Popen(
File "C:\Users\Shahid\AppData\Local\Programs\Python\Python310\lib\subprocess.py", line 971, in init
self._execute_child(args, executable, preexec_fn, close_fds,
File "C:\Users\Shahid\AppData\Local\Programs\Python\Python310\lib\subprocess.py", line 1440, in _execute_child
hp, ht, pid, tid = _winapi.CreateProcess(executable, args,
FileNotFoundError: [WinError 2] The system cannot find the file specified

[glangford]

Do you have ffmpeg installed? whisper requires it.

[LaoshuBaby]

Sure, I meet with this problem, I configured PATH to downloaded ffmpeg binary but failed, then I install it with choco, then whisper work correctly. (but still using FP32 because I only have a core graphics with AMD CPU)

[doveg]

As the log says, you're looking for a file called "audio.mp3" in your working directory.
I'm afraid you'll have to check it in the directory you pass in.

By the way, "using FP32 instead" means whisper will only use the CPU for the task, if you want to take advantage of the GPU, check out the PyTorch version for "cuda".

[sivakumar41]

C:\Users\Shahid\Desktop\Python Scripts\whisper-main\whisper\transcribe.py:79: UserWarning: FP16 is not supported on CPU; using FP32 instead warnings.warn("FP16 is not supported on CPU; using FP32 instead") Traceback (most recent call last): File "C:\Users\Shahid\Desktop\Python Scripts\whisper-main\main.py", line 4, in result = model.transcribe("audio.mp3") File "C:\Users\Shahid\Desktop\Python Scripts\whisper-main\whisper\transcribe.py", line 85, in transcribe mel = log_mel_spectrogram(audio) File "C:\Users\Shahid\Desktop\Python Scripts\whisper-main\whisper\audio.py", line 111, in log_mel_spectrogram audio = load_audio(audio) File "C:\Users\Shahid\Desktop\Python Scripts\whisper-main\whisper\audio.py", line 42, in load_audio ffmpeg.input(file, threads=0) File "C:\Users\Shahid\AppData\Local\Programs\Python\Python310\lib\site-packages\ffmpeg_run.py", line 313, in run process = run_async( File "C:\Users\Shahid\AppData\Local\Programs\Python\Python310\lib\site-packages\ffmpeg_run.py", line 284, in run_async return subprocess.Popen( File "C:\Users\Shahid\AppData\Local\Programs\Python\Python310\lib\subprocess.py", line 971, in init self._execute_child(args, executable, preexec_fn, close_fds, File "C:\Users\Shahid\AppData\Local\Programs\Python\Python310\lib\subprocess.py", line 1440, in _execute_child hp, ht, pid, tid = _winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] The system cannot find the file specified

Did you solved it?

[glangford]

• FileNotFound error on Windows #61 (comment)
• [WinError 2] The system cannot find the file specified #109

[sivakumar41]

The file is in the correct position.
I'm not able to install all the dependencies.
That may be the reason for the error

Can you guide me to install all the required libraries in the windows operating system.
Thank you