Hugging Face's logo

bigmorning
/
train_from_raw_cv12_true__0095

Automatic Speech Recognition
Transformers
TensorFlow
whisper
generated_from_keras_callback
Inference Endpoints
Model card Files Community
bigmorning commited on
Commit
a4c1584
•
1 Parent(s): fc71881

Upload TFWhisperForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +151 -0
  2. config.json +64 -0
  3. generation_config.json +117 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: openai/whisper-tiny
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: train_from_raw_cv12_true__0095
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
+ probably proofread and complete it, then remove this comment. -->
13
+
14
+ # train_from_raw_cv12_true__0095
15
+
16
+ This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.0041
19
+ - Train Accuracy: 0.1114
20
+ - Train Wermet: 4.2042
21
+ - Validation Loss: 0.5504
22
+ - Validation Accuracy: 0.0645
23
+ - Validation Wermet: 9.8599
24
+ - Epoch: 94
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
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
44
+ - training_precision: float32
45
+
46
+ ### Training results
47
+
48
+ | Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
49
+ |:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
50
+ | 2.3396 | 0.0444 | 2.7124 | 1.8124 | 0.0331 | 9.4418 | 0 |
51
+ | 1.7496 | 0.0562 | 3.2708 | 1.6529 | 0.0359 | 9.7805 | 1 |
52
+ | 1.6254 | 0.0594 | 3.1714 | 1.5874 | 0.0371 | 10.4139 | 2 |
53
+ | 1.5490 | 0.0615 | 3.0208 | 1.5102 | 0.0382 | 8.2054 | 3 |
54
+ | 1.4910 | 0.0631 | 2.8298 | 1.4213 | 0.0402 | 8.9930 | 4 |
55
+ | 1.4233 | 0.0650 | 2.7100 | 1.3319 | 0.0421 | 8.8483 | 5 |
56
+ | 1.3203 | 0.0679 | 2.5125 | 1.1806 | 0.0450 | 7.0373 | 6 |
57
+ | 1.1453 | 0.0730 | 2.5001 | 1.0029 | 0.0484 | 5.7328 | 7 |
58
+ | 0.9537 | 0.0789 | 2.6295 | 0.7799 | 0.0529 | 6.7373 | 8 |
59
+ | 0.7822 | 0.0844 | 2.7501 | 0.6499 | 0.0556 | 8.5538 | 9 |
60
+ | 0.6317 | 0.0895 | 2.9507 | 0.5467 | 0.0578 | 8.4990 | 10 |
61
+ | 0.5010 | 0.0940 | 3.1604 | 0.4597 | 0.0597 | 9.4002 | 11 |
62
+ | 0.4026 | 0.0975 | 3.2910 | 0.3984 | 0.0610 | 9.8173 | 12 |
63
+ | 0.3372 | 0.0998 | 3.5302 | 0.3571 | 0.0619 | 9.6433 | 13 |
64
+ | 0.2922 | 0.1013 | 3.5614 | 0.3391 | 0.0623 | 9.6152 | 14 |
65
+ | 0.2572 | 0.1025 | 3.5685 | 0.3157 | 0.0628 | 9.4497 | 15 |
66
+ | 0.2258 | 0.1036 | 3.5179 | 0.3104 | 0.0630 | 9.7735 | 16 |
67
+ | 0.1995 | 0.1045 | 3.5362 | 0.2944 | 0.0634 | 9.8154 | 17 |
68
+ | 0.1762 | 0.1054 | 3.5227 | 0.2820 | 0.0637 | 9.8672 | 18 |
69
+ | 0.1551 | 0.1061 | 3.5489 | 0.2849 | 0.0638 | 9.6569 | 19 |
70
+ | 0.1356 | 0.1068 | 3.4990 | 0.2821 | 0.0639 | 9.9735 | 20 |
71
+ | 0.1174 | 0.1074 | 3.5119 | 0.2841 | 0.0640 | 9.8770 | 21 |
72
+ | 0.1016 | 0.1080 | 3.5233 | 0.2903 | 0.0640 | 10.0309 | 22 |
73
+ | 0.0847 | 0.1087 | 3.5368 | 0.3013 | 0.0640 | 9.8095 | 23 |
74
+ | 0.0713 | 0.1092 | 3.5250 | 0.3040 | 0.0640 | 9.7686 | 24 |
75
+ | 0.0596 | 0.1096 | 3.5310 | 0.3137 | 0.0640 | 9.9239 | 25 |
76
+ | 0.0478 | 0.1101 | 3.5776 | 0.3228 | 0.0641 | 10.2774 | 26 |
77
+ | 0.0400 | 0.1104 | 3.6155 | 0.3316 | 0.0641 | 9.9082 | 27 |
78
+ | 0.0301 | 0.1107 | 3.6545 | 0.3446 | 0.0641 | 9.9672 | 28 |
79
+ | 0.0227 | 0.1110 | 3.7827 | 0.3579 | 0.0641 | 10.2859 | 29 |
80
+ | 0.0179 | 0.1112 | 3.7672 | 0.3728 | 0.0640 | 10.1965 | 30 |
81
+ | 0.0148 | 0.1112 | 3.7575 | 0.3829 | 0.0641 | 10.5114 | 31 |
82
+ | 0.0116 | 0.1113 | 3.7682 | 0.3959 | 0.0641 | 10.4941 | 32 |
83
+ | 0.0100 | 0.1114 | 3.8332 | 0.4056 | 0.0641 | 10.6330 | 33 |
84
+ | 0.0140 | 0.1112 | 3.8661 | 0.4283 | 0.0638 | 10.5741 | 34 |
85
+ | 0.0159 | 0.1111 | 3.8054 | 0.4203 | 0.0640 | 10.5108 | 35 |
86
+ | 0.0085 | 0.1114 | 3.7278 | 0.4236 | 0.0641 | 10.3731 | 36 |
87
+ | 0.0052 | 0.1115 | 3.8251 | 0.4366 | 0.0641 | 10.5728 | 37 |
88
+ | 0.0058 | 0.1115 | 3.9767 | 0.4459 | 0.0641 | 10.5720 | 38 |
89
+ | 0.0074 | 0.1114 | 4.0721 | 0.4775 | 0.0637 | 10.9922 | 39 |
90
+ | 0.0133 | 0.1111 | 3.9087 | 0.4560 | 0.0640 | 9.8398 | 40 |
91
+ | 0.0072 | 0.1114 | 3.9828 | 0.4533 | 0.0642 | 10.7116 | 41 |
92
+ | 0.0045 | 0.1115 | 3.9705 | 0.4668 | 0.0641 | 10.9326 | 42 |
93
+ | 0.0050 | 0.1114 | 4.1288 | 0.4677 | 0.0641 | 10.5865 | 43 |
94
+ | 0.0057 | 0.1114 | 4.1164 | 0.4709 | 0.0642 | 10.9947 | 44 |
95
+ | 0.0148 | 0.1111 | 4.2062 | 0.4594 | 0.0643 | 10.5855 | 45 |
96
+ | 0.0053 | 0.1114 | 4.0964 | 0.4598 | 0.0644 | 10.9385 | 46 |
97
+ | 0.0024 | 0.1115 | 4.1318 | 0.4660 | 0.0644 | 11.2717 | 47 |
98
+ | 0.0018 | 0.1115 | 4.1024 | 0.4696 | 0.0644 | 11.0203 | 48 |
99
+ | 0.0024 | 0.1115 | 4.0167 | 0.4845 | 0.0642 | 10.2553 | 49 |
100
+ | 0.0065 | 0.1114 | 4.1337 | 0.5009 | 0.0640 | 10.6290 | 50 |
101
+ | 0.0085 | 0.1113 | 4.1551 | 0.4943 | 0.0642 | 10.7108 | 51 |
102
+ | 0.0051 | 0.1114 | 4.2572 | 0.4838 | 0.0644 | 11.0773 | 52 |
103
+ | 0.0029 | 0.1115 | 4.2158 | 0.4869 | 0.0644 | 10.8471 | 53 |
104
+ | 0.0029 | 0.1115 | 4.2389 | 0.4904 | 0.0644 | 10.9344 | 54 |
105
+ | 0.0076 | 0.1114 | 4.4629 | 0.5367 | 0.0637 | 10.0070 | 55 |
106
+ | 0.0109 | 0.1112 | 3.8409 | 0.4880 | 0.0644 | 10.0557 | 56 |
107
+ | 0.0026 | 0.1115 | 3.8716 | 0.4823 | 0.0645 | 10.3257 | 57 |
108
+ | 0.0014 | 0.1115 | 3.8076 | 0.4879 | 0.0645 | 10.2943 | 58 |
109
+ | 0.0008 | 0.1115 | 3.8851 | 0.4854 | 0.0646 | 10.3687 | 59 |
110
+ | 0.0009 | 0.1115 | 3.9626 | 0.5204 | 0.0643 | 10.2350 | 60 |
111
+ | 0.0114 | 0.1111 | 4.0524 | 0.4985 | 0.0643 | 10.5375 | 61 |
112
+ | 0.0051 | 0.1114 | 4.0766 | 0.4958 | 0.0645 | 10.3052 | 62 |
113
+ | 0.0022 | 0.1115 | 4.2414 | 0.4972 | 0.0645 | 10.6064 | 63 |
114
+ | 0.0018 | 0.1115 | 4.5264 | 0.5014 | 0.0645 | 10.4899 | 64 |
115
+ | 0.0033 | 0.1115 | 4.4869 | 0.5182 | 0.0644 | 9.8788 | 65 |
116
+ | 0.0048 | 0.1114 | 4.2916 | 0.5082 | 0.0644 | 10.8155 | 66 |
117
+ | 0.0039 | 0.1114 | 4.5326 | 0.5101 | 0.0644 | 12.0401 | 67 |
118
+ | 0.0025 | 0.1115 | 4.4297 | 0.5056 | 0.0645 | 10.9017 | 68 |
119
+ | 0.0025 | 0.1115 | 4.2703 | 0.5064 | 0.0646 | 11.1319 | 69 |
120
+ | 0.0018 | 0.1115 | 4.2014 | 0.5228 | 0.0644 | 10.4356 | 70 |
121
+ | 0.0046 | 0.1114 | 4.1774 | 0.5267 | 0.0644 | 11.5421 | 71 |
122
+ | 0.0070 | 0.1113 | 4.0521 | 0.5185 | 0.0644 | 11.1608 | 72 |
123
+ | 0.0045 | 0.1114 | 4.2080 | 0.5041 | 0.0646 | 10.4894 | 73 |
124
+ | 0.0018 | 0.1115 | 4.1639 | 0.5001 | 0.0647 | 10.9893 | 74 |
125
+ | 0.0012 | 0.1115 | 4.2831 | 0.5026 | 0.0647 | 11.1654 | 75 |
126
+ | 0.0026 | 0.1115 | 4.4333 | 0.5219 | 0.0645 | 11.3173 | 76 |
127
+ | 0.0056 | 0.1114 | 4.1342 | 0.5351 | 0.0643 | 10.6952 | 77 |
128
+ | 0.0045 | 0.1114 | 4.2413 | 0.5161 | 0.0645 | 10.2386 | 78 |
129
+ | 0.0024 | 0.1115 | 4.0259 | 0.5122 | 0.0646 | 9.9376 | 79 |
130
+ | 0.0020 | 0.1115 | 3.9288 | 0.5131 | 0.0646 | 10.5318 | 80 |
131
+ | 0.0015 | 0.1115 | 4.2598 | 0.5160 | 0.0647 | 10.0045 | 81 |
132
+ | 0.0014 | 0.1115 | 4.1082 | 0.5311 | 0.0645 | 9.7244 | 82 |
133
+ | 0.0061 | 0.1113 | 4.1157 | 0.5400 | 0.0644 | 10.6306 | 83 |
134
+ | 0.0041 | 0.1114 | 4.2934 | 0.5179 | 0.0646 | 10.7082 | 84 |
135
+ | 0.0019 | 0.1115 | 4.0879 | 0.5148 | 0.0646 | 11.0278 | 85 |
136
+ | 0.0021 | 0.1115 | 4.1005 | 0.5350 | 0.0645 | 10.6981 | 86 |
137
+ | 0.0023 | 0.1115 | 4.0001 | 0.5218 | 0.0647 | 11.4887 | 87 |
138
+ | 0.0019 | 0.1115 | 4.2459 | 0.5329 | 0.0646 | 10.6841 | 88 |
139
+ | 0.0019 | 0.1115 | 4.1767 | 0.5281 | 0.0646 | 10.8256 | 89 |
140
+ | 0.0063 | 0.1113 | 4.0552 | 0.5270 | 0.0646 | 10.1748 | 90 |
141
+ | 0.0031 | 0.1114 | 4.1025 | 0.5115 | 0.0648 | 10.4663 | 91 |
142
+ | 0.0011 | 0.1115 | 4.1763 | 0.5090 | 0.0648 | 10.9994 | 92 |
143
+ | 0.0010 | 0.1115 | 4.1623 | 0.5189 | 0.0648 | 10.6794 | 93 |
144
+ | 0.0041 | 0.1114 | 4.2042 | 0.5504 | 0.0645 | 9.8599 | 94 |
145
+
146
+
147
+ ### Framework versions
148
+
149
+ - Transformers 4.33.0.dev0
150
+ - TensorFlow 2.13.0
151
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-tiny",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 50257
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "classifier_proj_size": 256,
15
+ "d_model": 384,
16
+ "decoder_attention_heads": 6,
17
+ "decoder_ffn_dim": 1536,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 4,
20
+ "decoder_start_token_id": 50258,
21
+ "dropout": 0.0,
22
+ "encoder_attention_heads": 6,
23
+ "encoder_ffn_dim": 1536,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 4,
26
+ "eos_token_id": 50257,
27
+ "forced_decoder_ids": [
28
+ [
29
+ 1,
30
+ 50289
31
+ ],
32
+ [
33
+ 2,
34
+ 50359
35
+ ],
36
+ [
37
+ 3,
38
+ 50363
39
+ ]
40
+ ],
41
+ "init_std": 0.02,
42
+ "is_encoder_decoder": true,
43
+ "mask_feature_length": 10,
44
+ "mask_feature_min_masks": 0,
45
+ "mask_feature_prob": 0.0,
46
+ "mask_time_length": 10,
47
+ "mask_time_min_masks": 2,
48
+ "mask_time_prob": 0.05,
49
+ "max_length": 448,
50
+ "max_source_positions": 1500,
51
+ "max_target_positions": 448,
52
+ "median_filter_width": 7,
53
+ "model_type": "whisper",
54
+ "num_hidden_layers": 4,
55
+ "num_mel_bins": 80,
56
+ "pad_token_id": 50257,
57
+ "scale_embedding": false,
58
+ "suppress_tokens": [],
59
+ "torch_dtype": "float32",
60
+ "transformers_version": "4.33.0.dev0",
61
+ "use_cache": true,
62
+ "use_weighted_layer_sum": false,
63
+ "vocab_size": 51865
64
+ }
generation_config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "begin_suppress_tokens": [
4
+ 220,
5
+ 50257
6
+ ],
7
+ "bos_token_id": 50257,
8
+ "decoder_start_token_id": 50258,
9
+ "eos_token_id": 50257,
10
+ "forced_decoder_ids": [
11
+ [
12
+ 1,
13
+ 50259
14
+ ],
15
+ [
16
+ 2,
17
+ 50359
18
+ ],
19
+ [
20
+ 3,
21
+ 50363
22
+ ]
23
+ ],
24
+ "max_length": 448,
25
+ "pad_token_id": 50257,
26
+ "suppress_tokens": [
27
+ 1,
28
+ 2,
29
+ 7,
30
+ 8,
31
+ 9,
32
+ 10,
33
+ 14,
34
+ 25,
35
+ 26,
36
+ 27,
37
+ 28,
38
+ 29,
39
+ 31,
40
+ 58,
41
+ 59,
42
+ 60,
43
+ 61,
44
+ 62,
45
+ 63,
46
+ 90,
47
+ 91,
48
+ 92,
49
+ 93,
50
+ 359,
51
+ 503,
52
+ 522,
53
+ 542,
54
+ 873,
55
+ 893,
56
+ 902,
57
+ 918,
58
+ 922,
59
+ 931,
60
+ 1350,
61
+ 1853,
62
+ 1982,
63
+ 2460,
64
+ 2627,
65
+ 3246,
66
+ 3253,
67
+ 3268,
68
+ 3536,
69
+ 3846,
70
+ 3961,
71
+ 4183,
72
+ 4667,
73
+ 6585,
74
+ 6647,
75
+ 7273,
76
+ 9061,
77
+ 9383,
78
+ 10428,
79
+ 10929,
80
+ 11938,
81
+ 12033,
82
+ 12331,
83
+ 12562,
84
+ 13793,
85
+ 14157,
86
+ 14635,
87
+ 15265,
88
+ 15618,
89
+ 16553,
90
+ 16604,
91
+ 18362,
92
+ 18956,
93
+ 20075,
94
+ 21675,
95
+ 22520,
96
+ 26130,
97
+ 26161,
98
+ 26435,
99
+ 28279,
100
+ 29464,
101
+ 31650,
102
+ 32302,
103
+ 32470,
104
+ 36865,
105
+ 42863,
106
+ 47425,
107
+ 49870,
108
+ 50254,
109
+ 50258,
110
+ 50358,
111
+ 50359,
112
+ 50360,
113
+ 50361,
114
+ 50362
115
+ ],
116
+ "transformers_version": "4.33.0.dev0"
117
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acecafeb59d4601da0a48faa7e496a0308c3629fcec159ce83b4b6ba09d86e8a
3
+ size 151253960