Hugging Face's logo

mmtg
/
train-test-valid

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Model card Files Metrics Community
mmtg commited on
Commit
537cc0c
·
verified ·
1 Parent(s): f68b701

End of training

Browse files
Files changed (2) hide show
  1. README.md +10 -11
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: openai/whisper-base
6
  metrics:
7
  - wer
8
  model-index:
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.1774
21
- - Wer: 77.8102
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 1e-05
41
  - train_batch_size: 8
42
  - eval_batch_size: 4
43
  - seed: 42
@@ -45,22 +45,21 @@ The following hyperparameters were used during training:
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 500
47
  - training_steps: 5000
48
- - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-------:|:----:|:---------------:|:-------:|
54
- | 0.1714 | 16.1290 | 1000 | 0.7755 | 83.6835 |
55
- | 0.007 | 32.2581 | 2000 | 1.0282 | 72.9489 |
56
- | 0.0016 | 48.3871 | 3000 | 1.1176 | 76.2460 |
57
- | 0.0008 | 64.5161 | 4000 | 1.1594 | 78.8376 |
58
- | 0.0007 | 80.6452 | 5000 | 1.1774 | 77.8102 |
59
 
60
 
61
  ### Framework versions
62
 
63
  - Transformers 4.41.2
64
- - Pytorch 2.1.2
65
  - Datasets 2.19.2
66
  - Tokenizers 0.19.1
 
1
  ---
2
  license: apache-2.0
3
+ base_model: openai/whisper-base
4
  tags:
5
  - generated_from_trainer
 
6
  metrics:
7
  - wer
8
  model-index:
 
17
 
18
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.1366
21
+ - Wer: 73.2710
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 3e-05
41
  - train_batch_size: 8
42
  - eval_batch_size: 4
43
  - seed: 42
 
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 500
47
  - training_steps: 5000
 
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-------:|:----:|:---------------:|:-------:|
53
+ | 0.015 | 16.1290 | 1000 | 0.9646 | 78.6843 |
54
+ | 0.0014 | 32.2581 | 2000 | 1.0654 | 74.4364 |
55
+ | 0.0002 | 48.3871 | 3000 | 1.1048 | 70.1733 |
56
+ | 0.0001 | 64.5161 | 4000 | 1.1278 | 75.6939 |
57
+ | 0.0001 | 80.6452 | 5000 | 1.1366 | 73.2710 |
58
 
59
 
60
  ### Framework versions
61
 
62
  - Transformers 4.41.2
63
+ - Pytorch 2.1.2+cu121
64
  - Datasets 2.19.2
65
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1eb6c191823ad37dd0bb77b37b28cc0037f0649f0ab63f64c322e8e03d22b68
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcfe91566668ad2d77cfda6b2405ea75b90a58b6d35b89f1c43d0c05f2047ccb
3
  size 290403936