cjli/iban_wavlm_conformer

ESPnet2 ASR model

cjli/iban_wavlm_transformer

This model was trained using iban recipe in espnet.

Run recipe

Follow the ESPnet installation instructions first, then:

cd espnet/egs2/iban/asr1
./run.sh --skip_data_prep false --skip_train true --download_model cjli/iban_wavlm_transformer

Results

WER

dataset	Snt	Wrd	Corr	Sub	Del	Ins	Err	S.Err
decode_asr_asr_model_valid.acc.best/test	104	2226	71.2	23.8	5.1	2.3	31.2	94.2

CER

dataset	Snt	Wrd	Corr	Sub	Del	Ins	Err	S.Err
decode_asr_asr_model_valid.acc.best/test	104	13527	91.8	2.7	5.4	2.2	10.4	94.2

TER

dataset	Snt	Wrd	Corr	Sub	Del	Ins	Err	S.Err
decode_asr_asr_model_valid.acc.best/test	104	5758	81.2	10.9	7.8	2.7	21.4	94.2

Citing ESPnet

@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:

@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}
}