Hugging Face's logo

jlvdoorn
/
whisper-medium.en-atco2-asr

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
jlvdoorn commited on
Commit
bbb298b
•
1 Parent(s): d9c7c37

Model save

Browse files
Files changed (4) hide show
  1. README.md +68 -0
  2. generation_config.json +188 -0
  3. pytorch_model.bin +1 -1
  4. runs/Jan15_16-42-16_gpu015/events.out.tfevents.1705333338.gpu015 +2 -2
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: openai/whisper-medium.en
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: whisper-medium.en-atco2-asr
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-medium.en-atco2-asr
17
+
18
+ This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.9216
21
+ - Wer: 29.5819
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 128
42
+ - eval_batch_size: 128
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 10
47
+ - num_epochs: 100
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
53
+ | 0.9851 | 12.5 | 50 | 1.0968 | 24.1103 |
54
+ | 0.1295 | 25.0 | 100 | 0.9019 | 82.4288 |
55
+ | 0.0379 | 37.5 | 150 | 0.8000 | 26.4680 |
56
+ | 0.008 | 50.0 | 200 | 0.8494 | 27.2687 |
57
+ | 0.0052 | 62.5 | 250 | 0.8890 | 34.2527 |
58
+ | 0.0032 | 75.0 | 300 | 0.9108 | 28.4253 |
59
+ | 0.0027 | 87.5 | 350 | 0.9191 | 29.2260 |
60
+ | 0.0023 | 100.0 | 400 | 0.9216 | 29.5819 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.36.2
66
+ - Pytorch 2.1.2
67
+ - Datasets 2.15.0
68
+ - Tokenizers 0.15.0
generation_config.json ADDED
@@ -0,0 +1,188 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 11,
5
+ 4
6
+ ],
7
+ [
8
+ 14,
9
+ 1
10
+ ],
11
+ [
12
+ 14,
13
+ 12
14
+ ],
15
+ [
16
+ 14,
17
+ 14
18
+ ],
19
+ [
20
+ 15,
21
+ 4
22
+ ],
23
+ [
24
+ 16,
25
+ 0
26
+ ],
27
+ [
28
+ 16,
29
+ 4
30
+ ],
31
+ [
32
+ 16,
33
+ 9
34
+ ],
35
+ [
36
+ 17,
37
+ 12
38
+ ],
39
+ [
40
+ 17,
41
+ 14
42
+ ],
43
+ [
44
+ 18,
45
+ 7
46
+ ],
47
+ [
48
+ 18,
49
+ 10
50
+ ],
51
+ [
52
+ 18,
53
+ 15
54
+ ],
55
+ [
56
+ 20,
57
+ 0
58
+ ],
59
+ [
60
+ 20,
61
+ 3
62
+ ],
63
+ [
64
+ 20,
65
+ 9
66
+ ],
67
+ [
68
+ 20,
69
+ 14
70
+ ],
71
+ [
72
+ 21,
73
+ 12
74
+ ]
75
+ ],
76
+ "begin_suppress_tokens": [
77
+ 220,
78
+ 50256
79
+ ],
80
+ "bos_token_id": 50257,
81
+ "decoder_start_token_id": 50257,
82
+ "eos_token_id": 50256,
83
+ "forced_decoder_ids": [
84
+ [
85
+ 1,
86
+ 50362
87
+ ]
88
+ ],
89
+ "is_multilingual": false,
90
+ "max_initial_timestamp_index": 1,
91
+ "max_length": 448,
92
+ "no_timestamps_token_id": 50362,
93
+ "pad_token_id": 50256,
94
+ "return_timestamps": false,
95
+ "suppress_tokens": [
96
+ 1,
97
+ 2,
98
+ 7,
99
+ 8,
100
+ 9,
101
+ 10,
102
+ 14,
103
+ 25,
104
+ 26,
105
+ 27,
106
+ 28,
107
+ 29,
108
+ 31,
109
+ 58,
110
+ 59,
111
+ 60,
112
+ 61,
113
+ 62,
114
+ 63,
115
+ 90,
116
+ 91,
117
+ 92,
118
+ 93,
119
+ 357,
120
+ 366,
121
+ 438,
122
+ 532,
123
+ 685,
124
+ 705,
125
+ 796,
126
+ 930,
127
+ 1058,
128
+ 1220,
129
+ 1267,
130
+ 1279,
131
+ 1303,
132
+ 1343,
133
+ 1377,
134
+ 1391,
135
+ 1635,
136
+ 1782,
137
+ 1875,
138
+ 2162,
139
+ 2361,
140
+ 2488,
141
+ 3467,
142
+ 4008,
143
+ 4211,
144
+ 4600,
145
+ 4808,
146
+ 5299,
147
+ 5855,
148
+ 6329,
149
+ 7203,
150
+ 9609,
151
+ 9959,
152
+ 10563,
153
+ 10786,
154
+ 11420,
155
+ 11709,
156
+ 11907,
157
+ 13163,
158
+ 13697,
159
+ 13700,
160
+ 14808,
161
+ 15306,
162
+ 16410,
163
+ 16791,
164
+ 17992,
165
+ 19203,
166
+ 19510,
167
+ 20724,
168
+ 22305,
169
+ 22935,
170
+ 27007,
171
+ 30109,
172
+ 30420,
173
+ 33409,
174
+ 34949,
175
+ 40283,
176
+ 40493,
177
+ 40549,
178
+ 47282,
179
+ 49146,
180
+ 50257,
181
+ 50357,
182
+ 50358,
183
+ 50359,
184
+ 50360,
185
+ 50361
186
+ ],
187
+ "transformers_version": "4.36.2"
188
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5c28bb5eef3be1b9dab0bab3a9407e9d7c81aac66b34c4aaa6bccf0b81a35c2
3
  size 3055751318
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:373b86786ccfc639d1d36d142115ba82c7c96848e92f1fee76d62736b2421576
3
  size 3055751318
runs/Jan15_16-42-16_gpu015/events.out.tfevents.1705333338.gpu015 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:053a596973dc53268f9eaf29306c2da15679170368a416f9766fbde0c186ccc3
3
- size 10825
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0062077b000081d976e82b47a3a965c7bca1c9465db9877e9505c5a4a9668db
3
+ size 11179