Hugging Face's logo

kuan2
/
whisper-tiny-en-book

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kuan2 commited on
Commit
cdb0da7
·
verified ·
1 Parent(s): 95b704c

End of training

Browse files
Files changed (2) hide show
  1. README.md +114 -0
  2. generation_config.json +143 -0
README.md ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ base_model: openai/whisper-tiny.en
6
+ tags:
7
+ - generated_from_trainer
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: Whisper tiny Book
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # Whisper tiny Book
19
+
20
+ This model is a fine-tuned version of [openai/whisper-tiny.en](https://huggingface.co/openai/whisper-tiny.en) on the Book dataset dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.0251
23
+ - Wer: 1.9268
24
+ - Cer: 0.3553
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 1e-05
44
+ - train_batch_size: 16
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 100
50
+ - training_steps: 500
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
56
+ |:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|
57
+ | 3.9929 | 0.0709 | 10 | 3.3716 | 29.5761 | 10.8629 |
58
+ | 3.9386 | 0.1418 | 20 | 3.0177 | 28.4200 | 10.2030 |
59
+ | 3.375 | 0.2128 | 30 | 2.6123 | 27.7457 | 9.8477 |
60
+ | 3.0007 | 0.2837 | 40 | 2.2620 | 26.1079 | 9.0186 |
61
+ | 2.5946 | 0.3546 | 50 | 1.9080 | 23.6031 | 7.8849 |
62
+ | 2.1729 | 0.4255 | 60 | 1.5682 | 20.2312 | 6.7682 |
63
+ | 1.8715 | 0.4965 | 70 | 1.3811 | 18.5934 | 6.0914 |
64
+ | 1.6468 | 0.5674 | 80 | 1.2722 | 17.2447 | 5.7868 |
65
+ | 1.5396 | 0.6383 | 90 | 1.1741 | 15.7033 | 5.0254 |
66
+ | 1.4669 | 0.7092 | 100 | 1.0837 | 14.5472 | 4.6024 |
67
+ | 1.3851 | 0.7801 | 110 | 0.9828 | 11.4644 | 3.7394 |
68
+ | 1.2107 | 0.8511 | 120 | 0.9004 | 9.9229 | 3.0457 |
69
+ | 1.1375 | 0.9220 | 130 | 0.8206 | 9.7303 | 3.2318 |
70
+ | 0.9685 | 0.9929 | 140 | 0.7487 | 8.9595 | 2.7750 |
71
+ | 0.8194 | 1.0638 | 150 | 0.6772 | 8.2852 | 2.5719 |
72
+ | 0.7976 | 1.1348 | 160 | 0.6092 | 7.8998 | 2.5550 |
73
+ | 0.7104 | 1.2057 | 170 | 0.5373 | 7.5145 | 2.2335 |
74
+ | 0.6255 | 1.2766 | 180 | 0.4742 | 7.0328 | 2.0981 |
75
+ | 0.5621 | 1.3475 | 190 | 0.4145 | 6.5511 | 1.9966 |
76
+ | 0.5151 | 1.4184 | 200 | 0.3615 | 5.3950 | 1.5905 |
77
+ | 0.4697 | 1.4894 | 210 | 0.3107 | 5.3950 | 1.4890 |
78
+ | 0.4032 | 1.5603 | 220 | 0.2671 | 5.2023 | 1.4382 |
79
+ | 0.3962 | 1.6312 | 230 | 0.2254 | 4.6243 | 1.2183 |
80
+ | 0.3278 | 1.7021 | 240 | 0.1901 | 4.1426 | 1.1337 |
81
+ | 0.2661 | 1.7730 | 250 | 0.1614 | 3.9499 | 1.0660 |
82
+ | 0.2927 | 1.8440 | 260 | 0.1362 | 3.6609 | 0.9475 |
83
+ | 0.2197 | 1.9149 | 270 | 0.1165 | 3.5645 | 0.9306 |
84
+ | 0.1859 | 1.9858 | 280 | 0.0991 | 3.4682 | 0.9137 |
85
+ | 0.1446 | 2.0567 | 290 | 0.0885 | 3.6609 | 0.8799 |
86
+ | 0.13 | 2.1277 | 300 | 0.0770 | 3.8536 | 0.9475 |
87
+ | 0.1376 | 2.1986 | 310 | 0.0675 | 3.5645 | 0.8629 |
88
+ | 0.1107 | 2.2695 | 320 | 0.0610 | 3.2755 | 0.8291 |
89
+ | 0.1187 | 2.3404 | 330 | 0.0568 | 2.9865 | 0.7614 |
90
+ | 0.1173 | 2.4113 | 340 | 0.0521 | 2.8902 | 0.7445 |
91
+ | 0.0859 | 2.4823 | 350 | 0.0476 | 2.8902 | 0.7445 |
92
+ | 0.0933 | 2.5532 | 360 | 0.0440 | 2.4085 | 0.5922 |
93
+ | 0.0787 | 2.6241 | 370 | 0.0397 | 2.0231 | 0.4399 |
94
+ | 0.0901 | 2.6950 | 380 | 0.0363 | 1.7341 | 0.3215 |
95
+ | 0.0833 | 2.7660 | 390 | 0.0337 | 1.9268 | 0.4230 |
96
+ | 0.0751 | 2.8369 | 400 | 0.0325 | 2.0231 | 0.3723 |
97
+ | 0.071 | 2.9078 | 410 | 0.0311 | 2.0231 | 0.3723 |
98
+ | 0.068 | 2.9787 | 420 | 0.0298 | 1.9268 | 0.3553 |
99
+ | 0.0724 | 3.0496 | 430 | 0.0286 | 2.1195 | 0.4569 |
100
+ | 0.0484 | 3.1206 | 440 | 0.0277 | 2.1195 | 0.4569 |
101
+ | 0.0422 | 3.1915 | 450 | 0.0272 | 1.9268 | 0.3553 |
102
+ | 0.0536 | 3.2624 | 460 | 0.0266 | 2.0231 | 0.4399 |
103
+ | 0.0443 | 3.3333 | 470 | 0.0262 | 2.0231 | 0.4399 |
104
+ | 0.0465 | 3.4043 | 480 | 0.0257 | 1.9268 | 0.3553 |
105
+ | 0.0555 | 3.4752 | 490 | 0.0253 | 1.9268 | 0.3553 |
106
+ | 0.0467 | 3.5461 | 500 | 0.0251 | 1.9268 | 0.3553 |
107
+
108
+
109
+ ### Framework versions
110
+
111
+ - Transformers 4.42.4
112
+ - Pytorch 2.3.1+cu121
113
+ - Datasets 2.20.0
114
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "is_multilingual": false,
44
+ "max_initial_timestamp_index": 50,
45
+ "max_length": 448,
46
+ "no_timestamps_token_id": 50362,
47
+ "pad_token_id": 50256,
48
+ "prev_sot_token_id": 50360,
49
+ "return_timestamps": false,
50
+ "suppress_tokens": [
51
+ 1,
52
+ 2,
53
+ 7,
54
+ 8,
55
+ 9,
56
+ 10,
57
+ 14,
58
+ 25,
59
+ 26,
60
+ 27,
61
+ 28,
62
+ 29,
63
+ 31,
64
+ 58,
65
+ 59,
66
+ 60,
67
+ 61,
68
+ 62,
69
+ 63,
70
+ 90,
71
+ 91,
72
+ 92,
73
+ 93,
74
+ 357,
75
+ 366,
76
+ 438,
77
+ 532,
78
+ 685,
79
+ 705,
80
+ 796,
81
+ 930,
82
+ 1058,
83
+ 1220,
84
+ 1267,
85
+ 1279,
86
+ 1303,
87
+ 1343,
88
+ 1377,
89
+ 1391,
90
+ 1635,
91
+ 1782,
92
+ 1875,
93
+ 2162,
94
+ 2361,
95
+ 2488,
96
+ 3467,
97
+ 4008,
98
+ 4211,
99
+ 4600,
100
+ 4808,
101
+ 5299,
102
+ 5855,
103
+ 6329,
104
+ 7203,
105
+ 9609,
106
+ 9959,
107
+ 10563,
108
+ 10786,
109
+ 11420,
110
+ 11709,
111
+ 11907,
112
+ 13163,
113
+ 13697,
114
+ 13700,
115
+ 14808,
116
+ 15306,
117
+ 16410,
118
+ 16791,
119
+ 17992,
120
+ 19203,
121
+ 19510,
122
+ 20724,
123
+ 22305,
124
+ 22935,
125
+ 27007,
126
+ 30109,
127
+ 30420,
128
+ 33409,
129
+ 34949,
130
+ 40283,
131
+ 40493,
132
+ 40549,
133
+ 47282,
134
+ 49146,
135
+ 50257,
136
+ 50357,
137
+ 50358,
138
+ 50359,
139
+ 50360,
140
+ 50361
141
+ ],
142
+ "transformers_version": "4.42.4"
143
+ }