ESPnet2 ASR model

`espnet/DCASE23.AudioCaptioning.FineTuned`

This model was trained by Shikhar Bharadwaj using clotho_v2 recipe in espnet.

Demo: How to use in ESPnet2

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

cd espnet
git checkout 09779acc8f744a3bf0dc20f4c0ac7ba91df4736d
pip install -e .
cd egs2/clotho_v2/asr1
./run.sh --skip_data_prep false --skip_train true --download_model espnet/DCASE23.AudioCaptioning.FineTuned

RESULTS

Environments

date: Tue Nov 5 15:18:41 CST 2024
python version: 3.9.18 | packaged by conda-forge | (main, Dec 23 2023, 16:33:10) [GCC 12.3.0]
espnet version: espnet 202409
pytorch version: pytorch 2.4.0
Git hash: ac484495e6e3cbf58bd3d1175c607c3f05bf6898
- Commit date: Tue Nov 5 09:24:48 2024 -0600

exp/asr_ft_lr5e-5.initfix.bigbatch512.lr2e-4.weighted12layers.20241103.145125

=====================================================
 Split: evaluation Evaluation over 1045 predictions.
=====================================================
 cider_d             : 0.40163786973038024
 spice               : 0.12328679455316437
 spider              : 0.2624623321417723
 sbert_sim           : 0.5094392538748004
 fer                 : 0.03827751196172249
 fense               : 0.4915462823319092
 meteor              : 0.17194480402701573
 rouge_l             : 0.3550182495603068
 fer.add_tail_prob   : 0.04409123957157135
 fer.repeat_event_prob: 0.07279406487941742
 fer.repeat_adv_prob : 0.0016611652681604028
 fer.remove_conj_prob: 0.10949967056512833
 fer.remove_verb_prob: 0.20523187518119812
 fer.error_prob      : 0.319917231798172
 spider_fl           : 0.2532289450419614
=====================================================

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}
}