Hugging Face's logo

Udap10
/
whisper-small-Dzo

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Udap10 commited on
Commit
bfb69a6
·
verified ·
1 Parent(s): 96e96f4

End of training

Browse files
Files changed (4) hide show
  1. README.md +13 -3
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Jan22_08-16-20_a4970eb8e8c6/events.out.tfevents.1737533790.a4970eb8e8c6.1084.0 +2 -2
README.md CHANGED
@@ -4,6 +4,8 @@ license: apache-2.0
4
  base_model: openai/whisper-small
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: whisper-small-Dzo
9
  results: []
@@ -15,6 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
15
  # whisper-small-Dzo
16
 
17
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
 
 
 
18
 
19
  ## Model description
20
 
@@ -34,17 +39,22 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 1e-05
37
- - train_batch_size: 16
38
- - eval_batch_size: 4
39
  - seed: 42
40
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: linear
42
  - lr_scheduler_warmup_steps: 500
43
- - training_steps: 500
44
  - mixed_precision_training: Native AMP
45
 
46
  ### Training results
47
 
 
 
 
 
 
48
 
49
 
50
  ### Framework versions
 
4
  base_model: openai/whisper-small
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - wer
9
  model-index:
10
  - name: whisper-small-Dzo
11
  results: []
 
17
  # whisper-small-Dzo
18
 
19
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.6577
22
+ - Wer: 360.5263
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 1e-05
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
  - seed: 42
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
48
+ - training_steps: 0
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | No log | 1.0 | 20 | 1.5041 | 452.6316 |
56
+ | 1.5599 | 2.0 | 40 | 0.8098 | 489.4737 |
57
+ | 0.8495 | 3.0 | 60 | 0.6577 | 360.5263 |
58
 
59
 
60
  ### Framework versions
generation_config.json CHANGED
@@ -150,7 +150,7 @@
150
  "<|yo|>": 50325,
151
  "<|zh|>": 50260
152
  },
153
- "language": "dzo",
154
  "max_initial_timestamp_index": 50,
155
  "max_length": 448,
156
  "no_timestamps_token_id": 50363,
 
150
  "<|yo|>": 50325,
151
  "<|zh|>": 50260
152
  },
153
+ "language": "bo",
154
  "max_initial_timestamp_index": 50,
155
  "max_length": 448,
156
  "no_timestamps_token_id": 50363,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5d1e1d32ad0addd69d85fa0bdc996c8f8881bfbd04972b48fbe6947047f6683
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cde550b0003abb581a81c0cdcf5f9b84b4f575eb38480a5c4cbe4b16ae6a7cb
3
  size 966995080
runs/Jan22_08-16-20_a4970eb8e8c6/events.out.tfevents.1737533790.a4970eb8e8c6.1084.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4084b36577074b308ac0f793a3b4a69fa0fc489453713179024d200602556865
3
- size 7653
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b61da17d77cf6af0ab4f36f2029b0cb60c325d69c66c2316647279ed99b1b7a6
3
+ size 8520