---
tags:
- espnet
- audio
- automatic-speech-recognition
language: en
datasets:
- clotho_v2
license: cc-by-4.0
---

## ESPnet2 ASR model

### `espnet/DCASE23.AudioCaptioning.PreTrained`

This model was trained by Shikhar Bharadwaj using clotho_v2 recipe in [espnet](https://github.com/espnet/espnet/).

### Demo: How to use in ESPnet2

Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html)
if you haven't done that already.

```bash
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.aac.pt
```

<!-- Generated by scripts/utils/show_asr_result.sh -->
# RESULTS
## Environments
- date: `Mon Nov  4 13:48:05 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 202402`
- pytorch version: `pytorch 2.4.0`
- Git hash: `aa8910e107440c14a9e22e35e252c562e636552e`
  - Commit date: `Sun Oct 13 10:22:11 2024 -0500`

## exp/asr_pt.initfix.bigbatch512.lr2e-4.weighted12layers.20241103.145125/
```
=====================================================
 Split: evaluation Evaluation over 1045 predictions.
=====================================================
 cider_d             : 0.19368922695190316
 spice               : 0.0892430642605593
 spider              : 0.14146614560623122
 sbert_sim           : 0.47783581224140936
 fer                 : 0.5301435406698565
 fense               : 0.2520530143112799
 meteor              : 0.13875538640747337
 rouge_l             : 0.2737659351281743
 fer.add_tail_prob   : 0.2866000533103943
 fer.repeat_event_prob: 0.08905956894159317
 fer.repeat_adv_prob : 0.0013483789516612887
 fer.remove_conj_prob: 0.19881780445575714
 fer.remove_verb_prob: 0.3627748191356659
 fer.error_prob      : 0.6818609833717346
 spider_fl           : 0.07657683145973274
=====================================================
`

### 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}
}
```