DDTChen commited on
Commit
442cdca
·
verified ·
1 Parent(s): 330bc22

End of training

Browse files
README.md CHANGED
@@ -25,7 +25,7 @@ model-index:
25
  metrics:
26
  - name: Wer
27
  type: wer
28
- value: 39.41388829900191
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
35
 
36
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 0.1887
39
- - Wer: 39.4139
40
 
41
  ## Model description
42
 
@@ -62,17 +62,18 @@ The following hyperparameters were used during training:
62
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 500
65
- - training_steps: 2000
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:------:|:----:|:---------------:|:-------:|
72
- | 0.2011 | 0.7092 | 500 | 0.2146 | 43.8734 |
73
- | 0.0914 | 1.4184 | 1000 | 0.1948 | 40.3270 |
74
- | 0.0369 | 2.1277 | 1500 | 0.1906 | 39.2228 |
75
- | 0.027 | 2.8369 | 2000 | 0.1887 | 39.4139 |
 
76
 
77
 
78
  ### Framework versions
 
25
  metrics:
26
  - name: Wer
27
  type: wer
28
+ value: 40.28456147802081
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
35
 
36
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 0.2414
39
+ - Wer: 40.2846
40
 
41
  ## Model description
42
 
 
62
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 500
65
+ - training_steps: 5000
66
  - mixed_precision_training: Native AMP
67
 
68
  ### Training results
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Wer |
71
  |:-------------:|:------:|:----:|:---------------:|:-------:|
72
+ | 0.0244 | 1.4184 | 1000 | 0.2211 | 42.4506 |
73
+ | 0.0127 | 2.8369 | 2000 | 0.2259 | 41.6437 |
74
+ | 0.0017 | 4.2553 | 3000 | 0.2313 | 40.8792 |
75
+ | 0.0006 | 5.6738 | 4000 | 0.2385 | 40.2209 |
76
+ | 0.0005 | 7.0922 | 5000 | 0.2414 | 40.2846 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7198df8219cb3508cc3ebbc71f93650f7c56d5f57765ed9eb6d494955eff99f
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:597a4d9fce32c9ef301bfb472eaf9bc0b1b8aed08c9e51d917892eaccca0674d
3
  size 966995080
runs/Mar13_13-10-22_db946b8b8c60/events.out.tfevents.1741871423.db946b8b8c60.604.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4eeb3e78d04c878a1351041701cb7e49016cc637c4a1cea1df0095a7af1e2f34
3
- size 49668
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc59384ddd63f76df4b6fc802fa646f66cf107cb5e1dfae15cb19c453fd8c9a
3
+ size 50022