Update README.md
Browse files
README.md
CHANGED
@@ -15,25 +15,8 @@ license: cc-by-4.0
|
|
15 |
|
16 |
This model was trained by winniech using aishell3 recipe in [espnet](https://github.com/espnet/espnet/).
|
17 |
|
18 |
-
### Demo: How to use in ESPnet2
|
19 |
-
|
20 |
-
Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html)
|
21 |
-
if you haven't done that already.
|
22 |
-
|
23 |
-
```bash
|
24 |
-
cd espnet
|
25 |
-
git checkout b4423aa582b53c780ec21540e5134917ed8c450e
|
26 |
-
pip install -e .
|
27 |
-
cd egs2/aishell3/tts1
|
28 |
-
./run.sh --skip_data_prep false --skip_train true --download_model winniech/espnet2_pretrained_aishell3_vits_tts_train_raw_phn_pypinyin_g2p_phone
|
29 |
-
```
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
## TTS config
|
34 |
|
35 |
-
<details><summary>expand</summary>
|
36 |
-
|
37 |
```
|
38 |
config: conf/train.yaml
|
39 |
print_config: false
|
@@ -536,46 +519,3 @@ required:
|
|
536 |
version: '202301'
|
537 |
distributed: false
|
538 |
```
|
539 |
-
|
540 |
-
</details>
|
541 |
-
|
542 |
-
|
543 |
-
|
544 |
-
### Citing ESPnet
|
545 |
-
|
546 |
-
```BibTex
|
547 |
-
@inproceedings{watanabe2018espnet,
|
548 |
-
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},
|
549 |
-
title={{ESPnet}: End-to-End Speech Processing Toolkit},
|
550 |
-
year={2018},
|
551 |
-
booktitle={Proceedings of Interspeech},
|
552 |
-
pages={2207--2211},
|
553 |
-
doi={10.21437/Interspeech.2018-1456},
|
554 |
-
url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
|
555 |
-
}
|
556 |
-
|
557 |
-
|
558 |
-
|
559 |
-
|
560 |
-
@inproceedings{hayashi2020espnet,
|
561 |
-
title={{Espnet-TTS}: Unified, reproducible, and integratable open source end-to-end text-to-speech toolkit},
|
562 |
-
author={Hayashi, Tomoki and Yamamoto, Ryuichi and Inoue, Katsuki and Yoshimura, Takenori and Watanabe, Shinji and Toda, Tomoki and Takeda, Kazuya and Zhang, Yu and Tan, Xu},
|
563 |
-
booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
|
564 |
-
pages={7654--7658},
|
565 |
-
year={2020},
|
566 |
-
organization={IEEE}
|
567 |
-
}
|
568 |
-
```
|
569 |
-
|
570 |
-
or arXiv:
|
571 |
-
|
572 |
-
```bibtex
|
573 |
-
@misc{watanabe2018espnet,
|
574 |
-
title={ESPnet: End-to-End Speech Processing Toolkit},
|
575 |
-
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},
|
576 |
-
year={2018},
|
577 |
-
eprint={1804.00015},
|
578 |
-
archivePrefix={arXiv},
|
579 |
-
primaryClass={cs.CL}
|
580 |
-
}
|
581 |
-
```
|
|
|
15 |
|
16 |
This model was trained by winniech using aishell3 recipe in [espnet](https://github.com/espnet/espnet/).
|
17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
## TTS config
|
19 |
|
|
|
|
|
20 |
```
|
21 |
config: conf/train.yaml
|
22 |
print_config: false
|
|
|
519 |
version: '202301'
|
520 |
distributed: false
|
521 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|