Hugging Face's logo

Dev372
/
HarshDev-whisper-small-English_4000

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Dev372 commited on
Commit
15cd5f8
•
1 Parent(s): 06fb598

End of training

Browse files
Files changed (3) hide show
  1. README.md +80 -0
  2. generation_config.json +192 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ base_model: openai/whisper-small.en
6
+ tags:
7
+ - generated_from_trainer
8
+ datasets:
9
+ - Hani89/medical_asr_recording_dataset
10
+ metrics:
11
+ - wer
12
+ model-index:
13
+ - name: English Whisper Model
14
+ results:
15
+ - task:
16
+ name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
+ dataset:
19
+ name: Medical
20
+ type: Hani89/medical_asr_recording_dataset
21
+ args: 'split: test'
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 6.681238615664845
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # English Whisper Model
32
+
33
+ This model is a fine-tuned version of [openai/whisper-small.en](https://huggingface.co/openai/whisper-small.en) on the Medical dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.1085
36
+ - Wer: 6.6812
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 1e-05
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 8
58
+ - seed: 42
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 500
62
+ - training_steps: 4000
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-------:|:----:|:---------------:|:------:|
69
+ | 0.0268 | 3.0030 | 1000 | 0.1019 | 6.4189 |
70
+ | 0.0017 | 6.0060 | 2000 | 0.1010 | 5.6903 |
71
+ | 0.0012 | 9.0090 | 3000 | 0.1064 | 6.6302 |
72
+ | 0.0001 | 12.0120 | 4000 | 0.1085 | 6.6812 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.42.2
78
+ - Pytorch 2.1.2
79
+ - Datasets 2.20.0
80
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": [
81
+ 220,
82
+ 50256
83
+ ],
84
+ "bos_token_id": 50257,
85
+ "decoder_start_token_id": 50257,
86
+ "eos_token_id": 50256,
87
+ "forced_decoder_ids": [
88
+ [
89
+ 1,
90
+ 50362
91
+ ]
92
+ ],
93
+ "is_multilingual": false,
94
+ "max_initial_timestamp_index": 50,
95
+ "max_length": 448,
96
+ "no_timestamps_token_id": 50362,
97
+ "pad_token_id": 50256,
98
+ "prev_sot_token_id": 50360,
99
+ "suppress_tokens": [
100
+ 1,
101
+ 2,
102
+ 7,
103
+ 8,
104
+ 9,
105
+ 10,
106
+ 14,
107
+ 25,
108
+ 26,
109
+ 27,
110
+ 28,
111
+ 29,
112
+ 31,
113
+ 58,
114
+ 59,
115
+ 60,
116
+ 61,
117
+ 62,
118
+ 63,
119
+ 90,
120
+ 91,
121
+ 92,
122
+ 93,
123
+ 357,
124
+ 366,
125
+ 438,
126
+ 532,
127
+ 685,
128
+ 705,
129
+ 796,
130
+ 930,
131
+ 1058,
132
+ 1220,
133
+ 1267,
134
+ 1279,
135
+ 1303,
136
+ 1343,
137
+ 1377,
138
+ 1391,
139
+ 1635,
140
+ 1782,
141
+ 1875,
142
+ 2162,
143
+ 2361,
144
+ 2488,
145
+ 3467,
146
+ 4008,
147
+ 4211,
148
+ 4600,
149
+ 4808,
150
+ 5299,
151
+ 5855,
152
+ 6329,
153
+ 7203,
154
+ 9609,
155
+ 9959,
156
+ 10563,
157
+ 10786,
158
+ 11420,
159
+ 11709,
160
+ 11907,
161
+ 13163,
162
+ 13697,
163
+ 13700,
164
+ 14808,
165
+ 15306,
166
+ 16410,
167
+ 16791,
168
+ 17992,
169
+ 19203,
170
+ 19510,
171
+ 20724,
172
+ 22305,
173
+ 22935,
174
+ 27007,
175
+ 30109,
176
+ 30420,
177
+ 33409,
178
+ 34949,
179
+ 40283,
180
+ 40493,
181
+ 40549,
182
+ 47282,
183
+ 49146,
184
+ 50257,
185
+ 50357,
186
+ 50358,
187
+ 50359,
188
+ 50360,
189
+ 50361
190
+ ],
191
+ "transformers_version": "4.42.2"
192
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:194ca2ee8e8d7ee796fc2f3af53156ca321d082581bf2417cc597b3ac8e97f6c
3
  size 966992008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790ec57f878071317cd110a02fd296bcbb69f3d6ce5663528d408032396426a1
3
  size 966992008