Hugging Face's logo

espnet
/
OpenBEATS-Large-AudioCaptioner-AudioCaps

Automatic Speech Recognition
ESPnet
audio
Model card Files
xet
Community
Shikhar Bharadwaj commited on
Commit
eea4ede
·
1 Parent(s): e3a21a2

Update model

Browse files
Files changed (19) hide show
  1. README.md +0 -0
  2. meta.yaml +8 -0
  3. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/config.yaml +0 -0
  4. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/acc.png +0 -0
  5. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/backward_time.png +0 -0
  6. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/cer.png +0 -0
  7. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/clip.png +0 -0
  8. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/forward_time.png +0 -0
  9. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/gpu_max_cached_mem_GB.png +0 -0
  10. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/grad_norm.png +0 -0
  11. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/iter_time.png +0 -0
  12. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/loss.png +0 -0
  13. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/loss_att.png +0 -0
  14. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/loss_scale.png +0 -0
  15. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/optim0_lr0.png +0 -0
  16. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/optim_step_time.png +0 -0
  17. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/train_time.png +0 -0
  18. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/wer.png +0 -0
  19. work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/valid.acc.ave_5best.pth +3 -0
README.md ADDED
The diff for this file is too large to render. See raw diff
 
meta.yaml ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ espnet: '202503'
2
+ files:
3
+ asr_model_file: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/valid.acc.ave_5best.pth
4
+ python: "3.9.18 | packaged by conda-forge | (main, Dec 23 2023, 17:20:25) \n[GCC 12.3.0]"
5
+ timestamp: 1763334080.358429
6
+ torch: 2.1.2
7
+ yaml_files:
8
+ asr_train_config: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/config.yaml
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/config.yaml ADDED
The diff for this file is too large to render. See raw diff
 
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/acc.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/backward_time.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/cer.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/clip.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/forward_time.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/gpu_max_cached_mem_GB.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/grad_norm.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/iter_time.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/loss.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/loss_att.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/loss_scale.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/optim0_lr0.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/optim_step_time.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/train_time.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/images/wer.png ADDED
work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audiocaps_aac/asr_earlargei2.l19/valid.acc.ave_5best.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09211f8ffb45e4b188bedf02d3b08d4e4c2cbdedc78dd2bd752444cdd5f109c
3
+ size 1958334508