-
Notifications
You must be signed in to change notification settings - Fork 1.9k
PaddleSpeech CLI Model List
zxcd edited this page Jan 10, 2023
·
8 revisions
| Model | Code-Switch | Language | Sample Rate |
|---|---|---|---|
| conformer_wenetspeech | False | zh | 16k |
| conformer_online_wenetspeech | False | zh | 16k |
| conformer_u2pp_online_wenetspeech | False | zh | 16k |
| conformer_online_multicn | False | zh | 16k |
| conformer_aishell | False | zh | 16k |
| conformer_online_aishell | False | zh | 16k |
| transformer_librispeech | False | en | 16k |
| deepspeech2online_wenetspeech | False | zh | 16k |
| deepspeech2offline_aishell | False | zh | 16k |
| deepspeech2online_aishell | False | zh | 16k |
| deepspeech2offline_librispeech | False | en | 16k |
| conformer_talcs | True | zh_en | 16k |
| Task | Model | Dataset | Lang | Speaker |
|---|---|---|---|---|
| AM | FastSpeech2 | CSMSC | zh | single, female |
| AM | FastSpeech2 | AISHELL3 | zh | multi-speaker |
| AM | FastSpeech2 | LJSpeech | en | single, female |
| AM | FastSpeech2 | VCTK | en | multi-speaker |
| AM | FastSpeech2-cnndecoder | CSMSC | zh | single, female |
| AM | FastSpeech2-mix | - | mix | - |
| AM | FastSpeech2-male | - | zh | - |
| AM | SpeedySpeech | CSMSC | zh | single, female |
| AM | Tacotron2 | CSMSC | zh | single, female |
| AM | Tacotron2 | LJSpeech | en | single, female |
| VOC | Parallel WaveGAN | CSMSC | zh | single, female |
| VOC | Parallel WaveGAN | AISHELL3 | zh | multi-speaker |
| VOC | Parallel WaveGAN | LJSpeech | en | single, female |
| VOC | Parallel WaveGAN | VCTK | en | multi-speaker |
| VOC | Parallel WaveGAN-male | - | zh | - |
| VOC | Multi Band MelGAN | CSMSC | zh | single, female |
| VOC | Style MelGAN | CSMSC | zh | single, female |
| VOC | HiFiGAN | CSMSC | zh | single, female |
| VOC | HiFiGAN | LJSpeech | en | single, female |
| VOC | HiFiGAN | AISHELL3 | zh | multi-speaker |
| VOC | HiFiGAN | VCTK | en | multi-speaker |
| VOC | WaveRNN | CSMSC | zh | single, female |
| Task | Model | Dataset | Sample Rate |
|---|---|---|---|
| CLS | panns_cnn6 | Audioset | 32k |
| CLS | panns_cnn10 | Audioset | 32k |
| CLS | panns_cnn14 | Audioset | 32k |
| Task | Model | Dataset | Sample Rate |
|---|---|---|---|
| Speaker Verification | ECAPA-TDNN | VoxCeleb | 16k |
| Task | Model | Dataset |
|---|---|---|
| en_to_zh | fat_st_ted | Ted-En-Zh |
| Task | Model | Dataset | Lang |
|---|---|---|---|
| punc | ernie_linear_p7_wudao | IWSLT2012-Zh | zh |
| punc | ernie_linear_p3_wudao | IWSLT2012-Zh | zh |
| punc | ernie_linear_p3_wudao_fast | IWSLT2012-Zh | zh |
| Task | Model | Dataset | Lang |
|---|---|---|---|
| KWS | MDTC | HeySnips | en |
| Model | Language | Sample Rate |
|---|---|---|
| wav2vec2 | en | 16k |
| wav2vec2ASR_librispeech | en | 16k |
| wav2vec2 | zh | 16k |
| wav2vec2ASR_aishell1 | zh | 16k |
| Model | Size | Multilingual | Language | Sample Rate |
|---|---|---|---|---|
| whisper | large | multilingual | - | 16k |
| whisper | base | - | en | 16k |
| whisper | base | multilingual | - | 16k |
| whisper | medium | - | en | 16k |
| whisper | medium | multilingual | - | 16k |
| whisper | small | - | en | 16k |
| whisper | small | multilingual | - | 16k |
| whisper | tiny | - | en | 16k |
| whisper | tiny | multilingual | - | 16k |