brianyan918 commited on
Commit
f2cce15
1 Parent(s): 6bd2854
Files changed (1) hide show
  1. README.md +61 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - espnet
4
+ - audio
5
+ - automatic-speech-recognition
6
+ language: en
7
+ datasets:
8
+ - librispeech
9
+ license: cc-by-4.0
10
+ ---
11
+
12
+ ## Example ESPnet2 ASR model
13
+
14
+ ### `Shinji Watanabe/librispeech_asr_train_asr_transformer_e18_raw_bpe_sp_valid.acc.best`
15
+
16
+ ♻️ Imported from https://zenodo.org/record/3966501
17
+
18
+ This model was trained by Shinji Watanabe using librispeech recipe in [espnet](https://github.com/espnet/espnet/).
19
+
20
+
21
+
22
+ ### Demo: How to use in ESPnet2
23
+
24
+ ```python
25
+ # coming soon
26
+ ```
27
+
28
+ ### Citing ESPnet
29
+
30
+ ```BibTex
31
+ @inproceedings{watanabe2018espnet,
32
+ author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson {Enrique Yalta Soplin} and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
33
+ title={{ESPnet}: End-to-End Speech Processing Toolkit},
34
+ year={2018},
35
+ booktitle={Proceedings of Interspeech},
36
+ pages={2207--2211},
37
+ doi={10.21437/Interspeech.2018-1456},
38
+ url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
39
+ }
40
+ @inproceedings{hayashi2020espnet,
41
+ title={{Espnet-TTS}: Unified, reproducible, and integratable open source end-to-end text-to-speech toolkit},
42
+ 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},
43
+ booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
44
+ pages={7654--7658},
45
+ year={2020},
46
+ organization={IEEE}
47
+ }
48
+ ```
49
+
50
+ or arXiv:
51
+
52
+ ```bibtex
53
+ @misc{watanabe2018espnet,
54
+ title={ESPnet: End-to-End Speech Processing Toolkit},
55
+ author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Enrique Yalta Soplin and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
56
+ year={2018},
57
+ eprint={1804.00015},
58
+ archivePrefix={arXiv},
59
+ primaryClass={cs.CL}
60
+ }
61
+ ```