Hugging Face's logo

Dev372
/
Medical_tiny_en_1_1v_check_train

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Dev372 commited on
Commit
f676fd6
•
1 Parent(s): 29c7f68

End of training

Browse files
Files changed (3) hide show
  1. README.md +91 -0
  2. generation_config.json +149 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ base_model: openai/whisper-tiny.en
6
+ tags:
7
+ - generated_from_trainer
8
+ datasets:
9
+ - Dev372/Medical_STT_Dataset_1.1
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: Dev372/Medical_STT_Dataset_1.1
21
+ args: 'split: test'
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 6.554753584375714
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-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the Medical dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.1509
36
+ - Wer: 6.5548
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: 18
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: 1500
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:------:|:----:|:---------------:|:-------:|
69
+ | 1.3263 | 0.2825 | 100 | 1.1474 | 12.0219 |
70
+ | 0.8292 | 0.5650 | 200 | 0.8086 | 9.9840 |
71
+ | 0.5971 | 0.8475 | 300 | 0.5736 | 9.0597 |
72
+ | 0.2888 | 1.1299 | 400 | 0.3038 | 8.2465 |
73
+ | 0.172 | 1.4124 | 500 | 0.2112 | 7.5835 |
74
+ | 0.1499 | 1.6949 | 600 | 0.1839 | 7.0773 |
75
+ | 0.1347 | 1.9774 | 700 | 0.1693 | 6.6691 |
76
+ | 0.0977 | 2.2599 | 800 | 0.1650 | 6.7834 |
77
+ | 0.0966 | 2.5424 | 900 | 0.1578 | 7.0381 |
78
+ | 0.0877 | 2.8249 | 1000 | 0.1542 | 6.6462 |
79
+ | 0.0587 | 3.1073 | 1100 | 0.1539 | 6.5090 |
80
+ | 0.0642 | 3.3898 | 1200 | 0.1531 | 6.5646 |
81
+ | 0.0597 | 3.6723 | 1300 | 0.1518 | 6.5090 |
82
+ | 0.0754 | 3.9548 | 1400 | 0.1511 | 6.5254 |
83
+ | 0.0506 | 4.2373 | 1500 | 0.1509 | 6.5548 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.43.2
89
+ - Pytorch 2.1.2
90
+ - Datasets 2.20.0
91
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 1,
5
+ 0
6
+ ],
7
+ [
8
+ 2,
9
+ 0
10
+ ],
11
+ [
12
+ 2,
13
+ 5
14
+ ],
15
+ [
16
+ 3,
17
+ 0
18
+ ],
19
+ [
20
+ 3,
21
+ 1
22
+ ],
23
+ [
24
+ 3,
25
+ 2
26
+ ],
27
+ [
28
+ 3,
29
+ 3
30
+ ],
31
+ [
32
+ 3,
33
+ 4
34
+ ]
35
+ ],
36
+ "begin_suppress_tokens": [
37
+ 220,
38
+ 50256
39
+ ],
40
+ "bos_token_id": 50257,
41
+ "decoder_start_token_id": 50257,
42
+ "eos_token_id": 50256,
43
+ "forced_decoder_ids": [
44
+ [
45
+ 1,
46
+ 50362
47
+ ]
48
+ ],
49
+ "is_multilingual": false,
50
+ "max_initial_timestamp_index": 50,
51
+ "max_length": 448,
52
+ "no_timestamps_token_id": 50362,
53
+ "pad_token_id": 50256,
54
+ "prev_sot_token_id": 50360,
55
+ "return_timestamps": false,
56
+ "suppress_tokens": [
57
+ 1,
58
+ 2,
59
+ 7,
60
+ 8,
61
+ 9,
62
+ 10,
63
+ 14,
64
+ 25,
65
+ 26,
66
+ 27,
67
+ 28,
68
+ 29,
69
+ 31,
70
+ 58,
71
+ 59,
72
+ 60,
73
+ 61,
74
+ 62,
75
+ 63,
76
+ 90,
77
+ 91,
78
+ 92,
79
+ 93,
80
+ 357,
81
+ 366,
82
+ 438,
83
+ 532,
84
+ 685,
85
+ 705,
86
+ 796,
87
+ 930,
88
+ 1058,
89
+ 1220,
90
+ 1267,
91
+ 1279,
92
+ 1303,
93
+ 1343,
94
+ 1377,
95
+ 1391,
96
+ 1635,
97
+ 1782,
98
+ 1875,
99
+ 2162,
100
+ 2361,
101
+ 2488,
102
+ 3467,
103
+ 4008,
104
+ 4211,
105
+ 4600,
106
+ 4808,
107
+ 5299,
108
+ 5855,
109
+ 6329,
110
+ 7203,
111
+ 9609,
112
+ 9959,
113
+ 10563,
114
+ 10786,
115
+ 11420,
116
+ 11709,
117
+ 11907,
118
+ 13163,
119
+ 13697,
120
+ 13700,
121
+ 14808,
122
+ 15306,
123
+ 16410,
124
+ 16791,
125
+ 17992,
126
+ 19203,
127
+ 19510,
128
+ 20724,
129
+ 22305,
130
+ 22935,
131
+ 27007,
132
+ 30109,
133
+ 30420,
134
+ 33409,
135
+ 34949,
136
+ 40283,
137
+ 40493,
138
+ 40549,
139
+ 47282,
140
+ 49146,
141
+ 50257,
142
+ 50357,
143
+ 50358,
144
+ 50359,
145
+ 50360,
146
+ 50361
147
+ ],
148
+ "transformers_version": "4.43.2"
149
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cd0b5064975e26b4adc030bb00413e944349415ecc0a3fc56d8553186a5522d
3
  size 151060136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ea517138546d3fd92befb440b922276d001aba7e909f168c9d4caf39783db60
3
  size 151060136