Hugging Face's logo

Hiro-nguyen
/
whisper-small-hi

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Hiro-nguyen commited on
Commit
d2e7fed
•
1 Parent(s): 4d0bd4b

Model save

Browse files
Files changed (4) hide show
  1. README.md +22 -25
  2. generation_config.json +64 -9
  3. model.safetensors +1 -1
  4. runs/May22_14-24-02_z390-a/events.out.tfevents.1716388047.z390-a.1171.0 +2 -2
README.md CHANGED
@@ -1,27 +1,24 @@
1
  ---
2
- language:
3
- - en
4
  license: apache-2.0
5
- base_model: openai/whisper-base.en
6
  tags:
7
- - hf-asr-leaderboard
8
  - generated_from_trainer
9
  metrics:
10
  - wer
11
  model-index:
12
- - name: Whisper Base EN
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # Whisper Base EN
20
 
21
- This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the ADLINK dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0003
24
- - Wer: 1.2422
25
 
26
  ## Model description
27
 
@@ -52,23 +49,23 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Wer |
56
- |:-------------:|:------:|:----:|:---------------:|:-------:|
57
- | 1.5447 | 33.33 | 100 | 1.2099 | 11.4907 |
58
- | 0.4211 | 66.67 | 200 | 0.3868 | 1.5528 |
59
- | 0.0987 | 100.0 | 300 | 0.0761 | 1.8634 |
60
- | 0.006 | 133.33 | 400 | 0.0040 | 1.2422 |
61
- | 0.0011 | 166.67 | 500 | 0.0010 | 1.2422 |
62
- | 0.0006 | 200.0 | 600 | 0.0006 | 1.2422 |
63
- | 0.0004 | 233.33 | 700 | 0.0004 | 1.2422 |
64
- | 0.0003 | 266.67 | 800 | 0.0003 | 1.2422 |
65
- | 0.0003 | 300.0 | 900 | 0.0003 | 1.2422 |
66
- | 0.0003 | 333.33 | 1000 | 0.0003 | 1.2422 |
67
 
68
 
69
  ### Framework versions
70
 
71
- - Transformers 4.38.0.dev0
72
- - Pytorch 2.1.2+cu121
73
- - Datasets 2.16.1
74
- - Tokenizers 0.15.1
 
1
  ---
 
 
2
  license: apache-2.0
3
+ base_model: openai/whisper-small.en
4
  tags:
 
5
  - generated_from_trainer
6
  metrics:
7
  - wer
8
  model-index:
9
+ - name: whisper-small-hi
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # whisper-small-hi
17
 
18
+ This model is a fine-tuned version of [openai/whisper-small.en](https://huggingface.co/openai/whisper-small.en) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0002
21
+ - Wer: 1.5152
22
 
23
  ## Model description
24
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
54
+ | 1.1465 | 25.0 | 100 | 1.1124 | 9.6970 |
55
+ | 0.4228 | 50.0 | 200 | 0.4547 | 2.4242 |
56
+ | 0.0555 | 75.0 | 300 | 0.0459 | 1.8182 |
57
+ | 0.0022 | 100.0 | 400 | 0.0022 | 1.8182 |
58
+ | 0.0007 | 125.0 | 500 | 0.0008 | 1.5152 |
59
+ | 0.0004 | 150.0 | 600 | 0.0005 | 1.5152 |
60
+ | 0.0003 | 175.0 | 700 | 0.0003 | 1.5152 |
61
+ | 0.0002 | 200.0 | 800 | 0.0003 | 1.5152 |
62
+ | 0.0002 | 225.0 | 900 | 0.0003 | 1.5152 |
63
+ | 0.0002 | 250.0 | 1000 | 0.0002 | 1.5152 |
64
 
65
 
66
  ### Framework versions
67
 
68
+ - Transformers 4.41.0
69
+ - Pytorch 2.2.0a0+81ea7a4
70
+ - Datasets 2.19.1
71
+ - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -1,24 +1,80 @@
1
  {
2
  "alignment_heads": [
3
  [
4
- 3,
 
 
 
 
 
 
 
 
5
  3
6
  ],
7
  [
8
- 4,
9
- 7
10
  ],
11
  [
12
- 5,
13
- 1
14
  ],
15
  [
16
- 5,
17
  5
18
  ],
19
  [
20
- 5,
21
  7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  ]
23
  ],
24
  "begin_suppress_tokens": [
@@ -40,7 +96,6 @@
40
  "no_timestamps_token_id": 50362,
41
  "pad_token_id": 50256,
42
  "prev_sot_token_id": 50360,
43
- "return_timestamps": false,
44
  "suppress_tokens": [
45
  1,
46
  2,
@@ -133,5 +188,5 @@
133
  50360,
134
  50361
135
  ],
136
- "transformers_version": "4.38.0.dev0"
137
  }
 
1
  {
2
  "alignment_heads": [
3
  [
4
+ 6,
5
+ 6
6
+ ],
7
+ [
8
+ 7,
9
+ 0
10
+ ],
11
+ [
12
+ 7,
13
  3
14
  ],
15
  [
16
+ 7,
17
+ 8
18
  ],
19
  [
20
+ 8,
21
+ 2
22
  ],
23
  [
24
+ 8,
25
  5
26
  ],
27
  [
28
+ 8,
29
  7
30
+ ],
31
+ [
32
+ 9,
33
+ 0
34
+ ],
35
+ [
36
+ 9,
37
+ 4
38
+ ],
39
+ [
40
+ 9,
41
+ 8
42
+ ],
43
+ [
44
+ 9,
45
+ 10
46
+ ],
47
+ [
48
+ 10,
49
+ 0
50
+ ],
51
+ [
52
+ 10,
53
+ 1
54
+ ],
55
+ [
56
+ 10,
57
+ 2
58
+ ],
59
+ [
60
+ 10,
61
+ 3
62
+ ],
63
+ [
64
+ 10,
65
+ 6
66
+ ],
67
+ [
68
+ 10,
69
+ 11
70
+ ],
71
+ [
72
+ 11,
73
+ 2
74
+ ],
75
+ [
76
+ 11,
77
+ 4
78
  ]
79
  ],
80
  "begin_suppress_tokens": [
 
96
  "no_timestamps_token_id": 50362,
97
  "pad_token_id": 50256,
98
  "prev_sot_token_id": 50360,
 
99
  "suppress_tokens": [
100
  1,
101
  2,
 
188
  50360,
189
  50361
190
  ],
191
+ "transformers_version": "4.41.0"
192
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a7a116943dade05b64e5ee21d7cd4f79abe0d9d881fd63aa4ace6a17301913a
3
  size 966992008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:126d56ec5748212114c3783abf1a53432dfa496d5d033151cf60744f58dcd213
3
  size 966992008
runs/May22_14-24-02_z390-a/events.out.tfevents.1716388047.z390-a.1171.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b209290bf5c25d1ffc1aca417ff761449eabf2376a319c6ade5b22557b1c172a
3
- size 13700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b43bfb9d6e5e8095890fd6feceeb50c6b0b6a3c99ab5890298825c0a01284ef
3
+ size 17540