Modelpublic

espnet/yoshiki_wsj_whisper_medium_finetuning

sourceHugging Facecc-by-4.0updated 5d agoView on Hugging Face

0likes10downloads

Model Card

Usage

python

import librosa
from espnet2.bin.asr_inference import Speech2Text

speech2text = Speech2Text.from_pretrained(model_tag="espnet/yoshiki_wsj_whisper_medium_finetuning")
# librosa resamples and mixes to one channel, so any file works; 16000 is
# what nearly every espnet recogniser is trained on - check this model's
# config if its audio is not 16 kHz
speech, rate = librosa.load("audio.wav", sr=16000, mono=True)
text, *_ = speech2text(speech)[0]
print(text)

ESPnet2 ASR model

`espnet/yoshiki_wsj_whisper_medium_finetuning`

This model was trained by Yoshiki using wsj recipe in espnet.

Demo: How to use in ESPnet2

Follow the ESPnet installation instructions if you haven't done that already.

bash

cd espnet
git checkout fe00740b80cd26fad7c550cd9e975609deb664db
pip install -e .
cd egs2/wsj/asr1
./run.sh --skip_data_prep false --skip_train true --download_model espnet/yoshiki_wsj_whisper_medium_finetuning

RESULTS

Environments

—date: Fri Jul 21 12:47:17 JST 2023
—python version: 3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]
—espnet version: espnet 202304
—pytorch version: pytorch 1.13.1
—Git hash: d7172fcb7181ffdcca9c0061400254b63e37bf21
—Commit date: Sat Jul 15 15:01:30 2023 +0900

/scratch/espnet-hackathon/egs2/wsj/asr1/exp/asrtrainasrwhisperfullwarmup3000rawenwhisper_multilingual

WER

dataset	Snt	Wrd	Corr	Sub	Del	Ins	Err	S.Err
decodeasrwhispernoctcgreedyasrmodelvalid.acc.ave/testeval92	333	5564	98.5	1.4	0.1	0.2	1.7	19.5

CER

dataset	Snt	Wrd	Corr	Sub	Del	Ins	Err	S.Err
decodeasrwhispernoctcgreedyasrmodelvalid.acc.ave/testeval92	333	32096	99.6	0.2	0.2	0.2	0.6	19.5

TER

dataset	Snt	Wrd	Corr	Sub	Del	Ins	Err	S.Err

/scratch/espnet-hackathon/egs2/wsj/asr1/exp/asrtrainasrwhisperfullwarmup3000rawenwhispermultilingual/decodeasrwhispernoctcgreedyasrmodelvalid.acc.ave

WER

dataset	Snt	Wrd	Corr	Sub	Del	Ins	Err	S.Err
org/test_dev93	503	8132	97.7	2.0	0.4	0.3	2.6	24.9

CER

dataset	Snt	Wrd	Corr	Sub	Del	Ins	Err	S.Err
org/test_dev93	503	46683	99.4	0.3	0.3	0.2	0.8	24.9

Citing ESPnet

BibTex

@inproceedings{watanabe2018espnet,
  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
  title={{ESPnet}: End-to-End Speech Processing Toolkit},
  year={2018},
  booktitle={Proceedings of Interspeech},
  pages={2207--2211},
  doi={10.21437/Interspeech.2018-1456},
  url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
}

or arXiv:

bibtex

@misc{watanabe2018espnet,
  title={ESPnet: End-to-End Speech Processing Toolkit},
  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
  year={2018},
  eprint={1804.00015},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}