Hugging Face's logo

jethrowang
/
vanilla-whisper-medium_evaluated_on_iOS

TensorBoard
Safetensors
Chinese
whisper
Generated from Trainer
Model card Files
xet
Metrics Community
jethrowang commited on
Commit
080acbc
·
verified ·
1 Parent(s): 6e4c2c3

End of training

Browse files
Files changed (5) hide show
  1. README.md +8 -8
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Aug18_00-02-48_SOTA/events.out.tfevents.1723912702.SOTA.236336.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the HAT ASR Aligned dataset.
21
  It achieves the following results on the evaluation set:
22
- - eval_loss: 0.0397
23
- - eval_cer: 1.4726
24
- - eval_runtime: 4296.3688
25
- - eval_samples_per_second: 1.061
26
- - eval_steps_per_second: 0.033
27
  - step: 0
28
 
29
  ## Model description
@@ -45,12 +45,12 @@ More information needed
45
  The following hyperparameters were used during training:
46
  - learning_rate: 1e-05
47
  - train_batch_size: 32
48
- - eval_batch_size: 32
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - lr_scheduler_warmup_steps: 488
53
- - training_steps: 4880
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the HAT ASR Aligned dataset.
21
  It achieves the following results on the evaluation set:
22
+ - eval_loss: 0.0216
23
+ - eval_cer: 0.7744
24
+ - eval_runtime: 2129.3072
25
+ - eval_samples_per_second: 2.141
26
+ - eval_steps_per_second: 0.134
27
  - step: 0
28
 
29
  ## Model description
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 1e-05
47
  - train_batch_size: 32
48
+ - eval_batch_size: 16
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_steps: 1521
53
+ - training_steps: 15215
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/share/nas169/jethrowang/CADA-GAN/whisper/results/vanilla-whisper-medium/checkpoint-4880",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
 
1
  {
2
+ "_name_or_path": "/share/nas169/jethrowang/CADA-GAN/whisper/results/vanilla-whisper-medium/checkpoint-15215",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
  "apply_spec_augment": false,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d45e0f74847ac9e140b535f36edc7da9ee71fe0ce2848424c588b2bc3c2cb45
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a706dc3a8ff4d46a0f73fb4e85c3b8cadeecd40e698f0496a14cf93b810cbcf4
3
  size 3055544304
runs/Aug18_00-02-48_SOTA/events.out.tfevents.1723912702.SOTA.236336.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:584c32a5f322da3f16dca4deeea6dd4639c1789133bbcd0ad71b4a119b943e2e
3
+ size 341
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8aaa26b369acb8cfe682185ef57568cff0f37f26de44f5bbabcb81b106ed1fa8
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f18f08d496128a2986ce73155d1a148cfac855fb14df2ea8d9be831ea3183a
3
  size 5304