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:
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
Missing feats_stats.npz
#1
by akreal - opened
Thank you for this great model!
An attempt to load the model fails with this message:
No such file or directory: 'exp/s2t_stats_raw_bpe40000/train/feats_stats.npz'
Could you please upload this file too?
Thanks for testing it, I’ve uploaded the file!
Wow, that was fast!
Now it works, thank you so much.
akreal changed discussion status to closed