Hugging Face's logo

espnet
/
DCASE23.AudioCaptioning.FineTuned

ESPnet
English
audio
audio_captioning
Model card Files Community
shikhar7ssu commited on
Commit
e7d1aab
·
verified ·
1 Parent(s): 1406eb8

Upload 19 files

Browse files
Files changed (19) hide show
  1. exp/asr_ft/8epoch.pth +3 -0
  2. exp/asr_ft/RESULTS.md +29 -0
  3. exp/asr_ft/config.yaml +0 -0
  4. exp/asr_ft/images/acc.png +0 -0
  5. exp/asr_ft/images/backward_time.png +0 -0
  6. exp/asr_ft/images/cer.png +0 -0
  7. exp/asr_ft/images/clip.png +0 -0
  8. exp/asr_ft/images/forward_time.png +0 -0
  9. exp/asr_ft/images/gpu_max_cached_mem_GB.png +0 -0
  10. exp/asr_ft/images/grad_norm.png +0 -0
  11. exp/asr_ft/images/iter_time.png +0 -0
  12. exp/asr_ft/images/loss.png +0 -0
  13. exp/asr_ft/images/loss_att.png +0 -0
  14. exp/asr_ft/images/loss_scale.png +0 -0
  15. exp/asr_ft/images/optim0_lr0.png +0 -0
  16. exp/asr_ft/images/optim_step_time.png +0 -0
  17. exp/asr_ft/images/train_time.png +0 -0
  18. exp/asr_ft/images/wer.png +0 -0
  19. meta.yaml +8 -0
exp/asr_ft/8epoch.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a4e5e654c50c9a1b2ae88efd3419b049f214ec8e1ca390c69c79ca505d20bc4
3
+ size 1005224328
exp/asr_ft/RESULTS.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!-- Generated by scripts/utils/show_asr_result.sh -->
2
+ # RESULTS
3
+ ## Environments
4
+ - date: `Fri Nov 29 20:06:53 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_ft
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
+ |inference_ctc_weight0.0_hugging_face_decoderTrue_asr_model_valid.acc.ave_5best/evaluation|1045|0|0.0|0.0|0.0|0.0|0.0|100.0|
18
+
19
+ ### CER
20
+
21
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
22
+ |---|---|---|---|---|---|---|---|---|
23
+ |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|
24
+ |inference_ctc_weight0.0_hugging_face_decoderTrue_asr_model_valid.acc.ave_5best/evaluation|1045|0|0.0|0.0|0.0|0.0|0.0|100.0|
25
+
26
+ ### TER
27
+
28
+ |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
29
+ |---|---|---|---|---|---|---|---|---|
exp/asr_ft/config.yaml ADDED
The diff for this file is too large to render. See raw diff
 
exp/asr_ft/images/acc.png ADDED
exp/asr_ft/images/backward_time.png ADDED
exp/asr_ft/images/cer.png ADDED
exp/asr_ft/images/clip.png ADDED
exp/asr_ft/images/forward_time.png ADDED
exp/asr_ft/images/gpu_max_cached_mem_GB.png ADDED
exp/asr_ft/images/grad_norm.png ADDED
exp/asr_ft/images/iter_time.png ADDED
exp/asr_ft/images/loss.png ADDED
exp/asr_ft/images/loss_att.png ADDED
exp/asr_ft/images/loss_scale.png ADDED
exp/asr_ft/images/optim0_lr0.png ADDED
exp/asr_ft/images/optim_step_time.png ADDED
exp/asr_ft/images/train_time.png ADDED
exp/asr_ft/images/wer.png ADDED
meta.yaml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ espnet: '202409'
2
+ files:
3
+ asr_model_file: exp/asr_ft/8epoch.pth
4
+ python: "3.9.20 (main, Oct 3 2024, 07:27:41) \n[GCC 11.2.0]"
5
+ timestamp: 1732975488.066304
6
+ torch: 2.4.0
7
+ yaml_files:
8
+ asr_train_config: exp/asr_ft/config.yaml