Automatic Speech Recognition
ESPnet
multilingual
audio
phone-recognition
grapheme-to-phoneme
phoneme-to-grapheme
Instructions to use espnet/powsm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/powsm with ESPnet:
import soundfile from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/powsm" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
Commit History
-
Create meta.yaml
Verified signaturec02412d -
Upload textnorm_retrained/exp/s2t_train_ctc3_conv2d_size768_e9_d9_mel128_raw_bpe40000/config.yaml with huggingface_hub
Verified signatured358132 -
Upload textnorm_retrained/exp/s2t_train_ctc3_conv2d_size768_e9_d9_mel128_raw_bpe40000/valid.acc.ave_5best.till45epoch.pth with huggingface_hub
Verified signatureb41811f -
Upload textnorm_retrained/exp/s2t_stats_raw_bpe40000/train/feats_stats.npz with huggingface_hub
Verified signature42436d8 -
Rename updated/data/token_list/bpe_unigram40000/bpe.model to textnorm_retrained/data/token_list/bpe_unigram40000/bpe.model
Verified signature4160def