akreal commited on
Commit
fbcffbb
1 Parent(s): 592d857

Update model

Browse files
Files changed (20) hide show
  1. README.md +69 -1
  2. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/RESULTS.md +0 -0
  3. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/config.yaml +0 -0
  4. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/acc.png +0 -0
  5. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/backward_time.png +0 -0
  6. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/cer.png +0 -0
  7. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/clip.png +0 -0
  8. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/forward_time.png +0 -0
  9. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/gpu_max_cached_mem_GB.png +0 -0
  10. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/grad_norm.png +0 -0
  11. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/iter_time.png +0 -0
  12. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/loss.png +0 -0
  13. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/loss_att.png +0 -0
  14. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/loss_scale.png +0 -0
  15. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/optim0_lr0.png +0 -0
  16. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/optim_step_time.png +0 -0
  17. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/train_time.png +0 -0
  18. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/wer.png +0 -0
  19. exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/valid.acc.ave_3best.pth +3 -0
  20. meta.yaml +8 -0
README.md CHANGED
@@ -1,3 +1,71 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - espnet
4
+ - audio
5
+ - automatic-speech-recognition
6
+ language: multilingual
7
+ datasets:
8
+ - fleurs
9
+ license: cc-by-4.0
10
  ---
11
+
12
+ ## ESPnet2 ASR model
13
+
14
+ ### `akreal/bloomzmms-aed-t`
15
+
16
+ This model was trained by Pavel Denisov using fleurs 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 99cc51a342acfd13ca2b7475bd32c636f467ca0f
26
+ pip install -e .
27
+ cd egs2/fleurs/asr1
28
+ ./run.sh --skip_data_prep false --skip_train true --download_model akreal/bloomzmms-aed-t
29
+ ```
30
+
31
+
32
+
33
+ ## ASR config
34
+
35
+ <details><summary>expand</summary>
36
+
37
+
38
+ </details>
39
+
40
+
41
+
42
+ ### Citing ESPnet
43
+
44
+ ```BibTex
45
+ @inproceedings{watanabe2018espnet,
46
+ 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},
47
+ title={{ESPnet}: End-to-End Speech Processing Toolkit},
48
+ year={2018},
49
+ booktitle={Proceedings of Interspeech},
50
+ pages={2207--2211},
51
+ doi={10.21437/Interspeech.2018-1456},
52
+ url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
53
+ }
54
+
55
+
56
+
57
+
58
+ ```
59
+
60
+ or arXiv:
61
+
62
+ ```bibtex
63
+ @misc{watanabe2018espnet,
64
+ title={ESPnet: End-to-End Speech Processing Toolkit},
65
+ 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},
66
+ year={2018},
67
+ eprint={1804.00015},
68
+ archivePrefix={arXiv},
69
+ primaryClass={cs.CL}
70
+ }
71
+ ```
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/RESULTS.md ADDED
File without changes
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/config.yaml ADDED
The diff for this file is too large to render. See raw diff
 
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/acc.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/backward_time.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/cer.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/clip.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/forward_time.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/gpu_max_cached_mem_GB.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/grad_norm.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/iter_time.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/loss.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/loss_att.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/loss_scale.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/optim0_lr0.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/optim_step_time.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/train_time.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/images/wer.png ADDED
exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/valid.acc.ave_3best.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cd18891c46cf7f2d9725a31b11eed93a208ac1c5596dbd7d43b1e9da0d3a5e9
3
+ size 16157622442
meta.yaml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ espnet: '202304'
2
+ files:
3
+ asr_model_file: exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/valid.acc.ave_3best.pth
4
+ python: "3.9.18 (main, Feb 28 2024, 00:00:00) \n[GCC 13.2.1 20231205 (Red Hat 13.2.1-6)]"
5
+ timestamp: 1711923144.164619
6
+ torch: 2.1.2+cu121
7
+ yaml_files:
8
+ asr_train_config: exp/asr_train_asr_e_branchformer_mms1b-asr_bloomz7b_aed-t_raw_hugging_face_bigscience-bloomz-7b1_sp/config.yaml