Hugging Face's logo

espnet
/
DCASE23.AudioCaptioning.PreTrained

Automatic Speech Recognition
ESPnet
English
audio
audio_captioning
Model card Files Community
shikhar7ssu commited on
Commit
f8585bb
·
verified ·
1 Parent(s): 417dcae

Upload 19 files

Browse files
Files changed (19) hide show
  1. exp/asr_pt/RESULTS.md +44 -0
  2. exp/asr_pt/config.yaml +0 -0
  3. exp/asr_pt/images/acc.png +0 -0
  4. exp/asr_pt/images/backward_time.png +0 -0
  5. exp/asr_pt/images/cer.png +0 -0
  6. exp/asr_pt/images/clip.png +0 -0
  7. exp/asr_pt/images/forward_time.png +0 -0
  8. exp/asr_pt/images/gpu_max_cached_mem_GB.png +0 -0
  9. exp/asr_pt/images/grad_norm.png +0 -0
  10. exp/asr_pt/images/iter_time.png +0 -0
  11. exp/asr_pt/images/loss.png +0 -0
  12. exp/asr_pt/images/loss_att.png +0 -0
  13. exp/asr_pt/images/loss_scale.png +0 -0
  14. exp/asr_pt/images/optim0_lr0.png +0 -0
  15. exp/asr_pt/images/optim_step_time.png +0 -0
  16. exp/asr_pt/images/train_time.png +0 -0
  17. exp/asr_pt/images/wer.png +0 -0
  18. exp/asr_pt/valid.acc.ave_5best.pth +3 -0
  19. meta.yaml +8 -0
exp/asr_pt/RESULTS.md ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!-- Generated by scripts/utils/show_asr_result.sh -->
2
+ # RESULTS
3
+ ## Environments
4
+ - date: `Fri Nov 29 14:59:50 EST 2024`
5
+ - python version: `3.9.20 (main, Oct 3 2024, 07:27:41) [GCC 11.2.0]`
6
+ - espnet version: `espnet 202409`
7
+ - pytorch version: `pytorch 2.4.0`
8
+ - Git hash: `65ea259e8effab5a43cdff87161a301dc0f20930`
9
+ - Commit date: `Fri Nov 29 10:54:44 2024 -0500`
10
+
11
+ ## exp/asr_pt
12
+ ### WER
13
+
14
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
15
+ |---|---|---|---|---|---|---|---|---|
16
+ |inference_ctc_weight0.0_hugging_face_decoderTrue_asr_model_latest/evaluation|1045|0|0.0|0.0|0.0|0.0|0.0|100.0|
17
+
18
+ ### CER
19
+
20
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
21
+ |---|---|---|---|---|---|---|---|---|
22
+ |inference_ctc_weight0.0_hugging_face_decoderTrue_asr_model_latest/evaluation|1045|0|0.0|0.0|0.0|0.0|0.0|100.0|
23
+
24
+ ### TER
25
+
26
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
27
+ |---|---|---|---|---|---|---|---|---|
28
+ ## exp/asr_pt/inference_ctc_weight0.0_hugging_face_decoderTrue_asr_model_latest
29
+ ### WER
30
+
31
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
32
+ |---|---|---|---|---|---|---|---|---|
33
+ |org/validation|1045|12004|15.7|76.4|7.9|35.7|120.0|100.0|
34
+
35
+ ### CER
36
+
37
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
38
+ |---|---|---|---|---|---|---|---|---|
39
+ |org/validation|1045|65932|45.5|39.4|15.1|39.4|93.9|100.0|
40
+
41
+ ### TER
42
+
43
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
44
+ |---|---|---|---|---|---|---|---|---|
exp/asr_pt/config.yaml ADDED
The diff for this file is too large to render. See raw diff
 
exp/asr_pt/images/acc.png ADDED
exp/asr_pt/images/backward_time.png ADDED
exp/asr_pt/images/cer.png ADDED
exp/asr_pt/images/clip.png ADDED
exp/asr_pt/images/forward_time.png ADDED
exp/asr_pt/images/gpu_max_cached_mem_GB.png ADDED
exp/asr_pt/images/grad_norm.png ADDED
exp/asr_pt/images/iter_time.png ADDED
exp/asr_pt/images/loss.png ADDED
exp/asr_pt/images/loss_att.png ADDED
exp/asr_pt/images/loss_scale.png ADDED
exp/asr_pt/images/optim0_lr0.png ADDED
exp/asr_pt/images/optim_step_time.png ADDED
exp/asr_pt/images/train_time.png ADDED
exp/asr_pt/images/wer.png ADDED
exp/asr_pt/valid.acc.ave_5best.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c159446630e96fee4fd74c8fedc5fc6c696dd7f703027444e4c4d84ff6c92a1c
3
+ size 1005400996
meta.yaml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ espnet: '202409'
2
+ files:
3
+ asr_model_file: exp/asr_pt/valid.acc.ave_5best.pth
4
+ python: "3.9.20 (main, Oct 3 2024, 07:27:41) \n[GCC 11.2.0]"
5
+ timestamp: 1732975453.840757
6
+ torch: 2.4.0
7
+ yaml_files:
8
+ asr_train_config: exp/asr_pt/config.yaml