LeVy4 commited on
Commit
0be120a
·
verified ·
1 Parent(s): 88c1bb5

LeVy4/whisper-small-v3

Browse files
README.md CHANGED
@@ -4,8 +4,6 @@ license: apache-2.0
4
  base_model: openai/whisper-small
5
  tags:
6
  - generated_from_trainer
7
- metrics:
8
- - wer
9
  model-index:
10
  - name: whisper-small-vi
11
  results: []
@@ -18,8 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0855
22
- - Wer: 14.0000
 
 
 
 
 
23
 
24
  ## Model description
25
 
@@ -48,25 +51,9 @@ The following hyperparameters were used during training:
48
  - training_steps: 1000
49
  - mixed_precision_training: Native AMP
50
 
51
- ### Training results
52
-
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
- |:-------------:|:-------:|:----:|:---------------:|:-------:|
55
- | 1.6255 | 5.5556 | 100 | 1.6181 | 67.0 |
56
- | 0.0811 | 11.1111 | 200 | 0.1741 | 24.0 |
57
- | 0.0031 | 16.6667 | 300 | 0.0962 | 17.0 |
58
- | 0.0007 | 22.2222 | 400 | 0.0863 | 15.0 |
59
- | 0.0004 | 27.7778 | 500 | 0.0860 | 15.0 |
60
- | 0.0002 | 33.3333 | 600 | 0.0855 | 14.0000 |
61
- | 0.0002 | 38.8889 | 700 | 0.0851 | 14.0000 |
62
- | 0.0002 | 44.4444 | 800 | 0.0854 | 14.0000 |
63
- | 0.0002 | 50.0 | 900 | 0.0855 | 14.0000 |
64
- | 0.0002 | 55.5556 | 1000 | 0.0855 | 14.0000 |
65
-
66
-
67
  ### Framework versions
68
 
69
- - Transformers 4.46.1
70
- - Pytorch 2.5.0+cu121
71
  - Datasets 3.1.0
72
- - Tokenizers 0.20.1
 
4
  base_model: openai/whisper-small
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: whisper-small-vi
9
  results: []
 
16
 
17
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - eval_loss: 0.1146
20
+ - eval_wer: 8.8000
21
+ - eval_runtime: 27.7238
22
+ - eval_samples_per_second: 2.777
23
+ - eval_steps_per_second: 0.361
24
+ - epoch: 25.9259
25
+ - step: 700
26
 
27
  ## Model description
28
 
 
51
  - training_steps: 1000
52
  - mixed_precision_training: Native AMP
53
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  ### Framework versions
55
 
56
+ - Transformers 4.46.3
57
+ - Pytorch 2.5.1+cu121
58
  - Datasets 3.1.0
59
+ - Tokenizers 0.20.3
generation_config.json CHANGED
@@ -250,5 +250,5 @@
250
  "transcribe": 50359,
251
  "translate": 50358
252
  },
253
- "transformers_version": "4.46.1"
254
  }
 
250
  "transcribe": 50359,
251
  "translate": 50358
252
  },
253
+ "transformers_version": "4.46.3"
254
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2aed9555cec644e4e6d58fe1cf469a23c4dc31b447de3266cb3d74fd0765016e
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00632590eda850d13ba6aebfb34da09d377d94793acfec1f46d18d7cc6f7770c
3
  size 966995080
runs/Nov26_03-43-04_5c673c481c2d/events.out.tfevents.1732592600.5c673c481c2d.605.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce0c89a0765d3cd9026f1183f6abf6f008b1b754d64f4947310bd246e4b9d1cc
3
- size 21331
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1f681253b1c94f700e90a220ae39dd5b46205761a8dc544671a7ff3876bce9f
3
+ size 24077