Hugging Face's logo

bigmorning
/
whisper_input_decoder_no_lob__0110

Automatic Speech Recognition
Transformers
TensorFlow
whisper
generated_from_keras_callback
Model card Files
xet
Community
bigmorning commited on
Commit
260efbd
·
1 Parent(s): 9e0e44b

Upload TFWhisperForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +166 -0
  2. config.json +51 -0
  3. generation_config.json +117 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: openai/whisper-tiny
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: whisper_input_decoder_no_lob__0110
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
+ # whisper_input_decoder_no_lob__0110
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: 0.0353
19
+ - Train Accuracy: 0.0361
20
+ - Train Wermet: 0.0258
21
+ - Validation Loss: 1.3977
22
+ - Validation Accuracy: 0.0208
23
+ - Validation Wermet: 0.3339
24
+ - Epoch: 109
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': 1e-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
+ | 5.4122 | 0.0107 | 0.9328 | 3.9759 | 0.0114 | 0.9606 | 0 |
51
+ | 4.7176 | 0.0116 | 0.8683 | 3.9404 | 0.0114 | 0.9334 | 1 |
52
+ | 4.6750 | 0.0117 | 0.8478 | 3.9211 | 0.0115 | 0.9237 | 2 |
53
+ | 4.6511 | 0.0117 | 0.8413 | 3.8864 | 0.0115 | 0.9331 | 3 |
54
+ | 4.6294 | 0.0118 | 0.8270 | 3.8729 | 0.0115 | 0.9228 | 4 |
55
+ | 4.6134 | 0.0118 | 0.8199 | 3.8690 | 0.0114 | 0.9451 | 5 |
56
+ | 4.5980 | 0.0118 | 0.8102 | 3.8491 | 0.0115 | 0.9152 | 6 |
57
+ | 4.5759 | 0.0119 | 0.7890 | 3.8366 | 0.0116 | 0.8691 | 7 |
58
+ | 4.5518 | 0.0120 | 0.7694 | 3.8081 | 0.0116 | 0.9013 | 8 |
59
+ | 4.5219 | 0.0121 | 0.7591 | 3.7734 | 0.0118 | 0.8383 | 9 |
60
+ | 4.4761 | 0.0122 | 0.7400 | 3.7156 | 0.0120 | 0.8125 | 10 |
61
+ | 4.4139 | 0.0125 | 0.7257 | 3.6311 | 0.0121 | 0.8188 | 11 |
62
+ | 4.3113 | 0.0128 | 0.7127 | 3.5089 | 0.0124 | 0.8008 | 12 |
63
+ | 4.1608 | 0.0132 | 0.7088 | 3.3587 | 0.0127 | 0.7742 | 13 |
64
+ | 3.9595 | 0.0138 | 0.7012 | 3.1493 | 0.0132 | 0.7718 | 14 |
65
+ | 3.7188 | 0.0145 | 0.6820 | 2.8784 | 0.0139 | 0.7292 | 15 |
66
+ | 3.4775 | 0.0153 | 0.6678 | 2.6716 | 0.0144 | 0.7074 | 16 |
67
+ | 3.2575 | 0.0160 | 0.6481 | 2.4980 | 0.0149 | 0.6764 | 17 |
68
+ | 3.0615 | 0.0167 | 0.6314 | 2.3456 | 0.0153 | 0.6476 | 18 |
69
+ | 2.8715 | 0.0174 | 0.6094 | 2.2090 | 0.0158 | 0.6210 | 19 |
70
+ | 2.6930 | 0.0181 | 0.5931 | 2.0918 | 0.0162 | 0.5992 | 20 |
71
+ | 2.5383 | 0.0187 | 0.5739 | 1.9769 | 0.0166 | 0.5791 | 21 |
72
+ | 2.3952 | 0.0193 | 0.5512 | 1.9042 | 0.0168 | 0.5589 | 22 |
73
+ | 2.2427 | 0.0201 | 0.5333 | 1.8028 | 0.0172 | 0.5394 | 23 |
74
+ | 2.1236 | 0.0206 | 0.5174 | 1.7434 | 0.0174 | 0.5240 | 24 |
75
+ | 2.0315 | 0.0211 | 0.4978 | 1.6755 | 0.0177 | 0.5084 | 25 |
76
+ | 1.9066 | 0.0217 | 0.4773 | 1.6534 | 0.0178 | 0.4947 | 26 |
77
+ | 1.8279 | 0.0221 | 0.4596 | 1.5606 | 0.0182 | 0.4788 | 27 |
78
+ | 1.7325 | 0.0227 | 0.4412 | 1.5173 | 0.0184 | 0.4667 | 28 |
79
+ | 1.6416 | 0.0232 | 0.4199 | 1.4733 | 0.0186 | 0.4511 | 29 |
80
+ | 1.5702 | 0.0236 | 0.4028 | 1.4519 | 0.0187 | 0.4442 | 30 |
81
+ | 1.4787 | 0.0241 | 0.3839 | 1.4213 | 0.0188 | 0.4322 | 31 |
82
+ | 1.4238 | 0.0244 | 0.3700 | 1.3971 | 0.0190 | 0.4272 | 32 |
83
+ | 1.3561 | 0.0249 | 0.3594 | 1.3499 | 0.0192 | 0.4171 | 33 |
84
+ | 1.2828 | 0.0254 | 0.3431 | 1.3555 | 0.0192 | 0.4097 | 34 |
85
+ | 1.2318 | 0.0257 | 0.3277 | 1.3183 | 0.0194 | 0.4035 | 35 |
86
+ | 1.1668 | 0.0262 | 0.3201 | 1.3068 | 0.0195 | 0.3978 | 36 |
87
+ | 1.1571 | 0.0261 | 0.3105 | 1.2901 | 0.0195 | 0.3916 | 37 |
88
+ | 1.0812 | 0.0267 | 0.2989 | 1.2720 | 0.0197 | 0.3860 | 38 |
89
+ | 1.0134 | 0.0273 | 0.2863 | 1.2593 | 0.0197 | 0.3777 | 39 |
90
+ | 0.9986 | 0.0273 | 0.2769 | 1.2629 | 0.0198 | 0.3754 | 40 |
91
+ | 0.9322 | 0.0279 | 0.2653 | 1.2320 | 0.0199 | 0.3694 | 41 |
92
+ | 0.9021 | 0.0281 | 0.2552 | 1.2308 | 0.0200 | 0.3651 | 42 |
93
+ | 0.8583 | 0.0284 | 0.2444 | 1.2199 | 0.0200 | 0.3614 | 43 |
94
+ | 0.8101 | 0.0288 | 0.2355 | 1.2120 | 0.0200 | 0.3597 | 44 |
95
+ | 0.8045 | 0.0288 | 0.2299 | 1.2023 | 0.0201 | 0.3567 | 45 |
96
+ | 0.7823 | 0.0290 | 0.2213 | 1.2075 | 0.0201 | 0.3529 | 46 |
97
+ | 0.7186 | 0.0296 | 0.2107 | 1.1917 | 0.0202 | 0.3530 | 47 |
98
+ | 0.6949 | 0.0298 | 0.2028 | 1.1926 | 0.0202 | 0.3465 | 48 |
99
+ | 0.6669 | 0.0300 | 0.1943 | 1.1902 | 0.0203 | 0.3446 | 49 |
100
+ | 0.6125 | 0.0305 | 0.1842 | 1.1892 | 0.0203 | 0.3437 | 50 |
101
+ | 0.5926 | 0.0307 | 0.1778 | 1.2058 | 0.0203 | 0.3450 | 51 |
102
+ | 0.6055 | 0.0305 | 0.1738 | 1.1859 | 0.0203 | 0.3394 | 52 |
103
+ | 0.5828 | 0.0307 | 0.1653 | 1.1921 | 0.0203 | 0.3379 | 53 |
104
+ | 0.5507 | 0.0311 | 0.1569 | 1.1906 | 0.0204 | 0.3385 | 54 |
105
+ | 0.5050 | 0.0315 | 0.1485 | 1.1834 | 0.0205 | 0.3361 | 55 |
106
+ | 0.4878 | 0.0316 | 0.1447 | 1.1815 | 0.0205 | 0.3329 | 56 |
107
+ | 0.4825 | 0.0317 | 0.1410 | 1.2096 | 0.0204 | 0.3359 | 57 |
108
+ | 0.4987 | 0.0315 | 0.1374 | 1.2000 | 0.0204 | 0.3352 | 58 |
109
+ | 0.4576 | 0.0319 | 0.1305 | 1.1868 | 0.0205 | 0.3329 | 59 |
110
+ | 0.4185 | 0.0323 | 0.1215 | 1.2043 | 0.0205 | 0.3322 | 60 |
111
+ | 0.3889 | 0.0326 | 0.1156 | 1.1853 | 0.0206 | 0.3302 | 61 |
112
+ | 0.3790 | 0.0327 | 0.1101 | 1.2028 | 0.0205 | 0.3316 | 62 |
113
+ | 0.4072 | 0.0324 | 0.1110 | 1.2502 | 0.0203 | 0.3309 | 63 |
114
+ | 0.3519 | 0.0330 | 0.1020 | 1.1959 | 0.0206 | 0.3284 | 64 |
115
+ | 0.3861 | 0.0326 | 0.1034 | 1.1885 | 0.0206 | 0.3271 | 65 |
116
+ | 0.3789 | 0.0326 | 0.0961 | 1.1969 | 0.0206 | 0.3298 | 66 |
117
+ | 0.3233 | 0.0332 | 0.0905 | 1.1922 | 0.0207 | 0.3280 | 67 |
118
+ | 0.2956 | 0.0335 | 0.0854 | 1.2003 | 0.0207 | 0.3296 | 68 |
119
+ | 0.2666 | 0.0339 | 0.0796 | 1.2141 | 0.0207 | 0.3252 | 69 |
120
+ | 0.3181 | 0.0333 | 0.0813 | 1.2133 | 0.0207 | 0.3302 | 70 |
121
+ | 0.3032 | 0.0335 | 0.0770 | 1.2170 | 0.0207 | 0.3315 | 71 |
122
+ | 0.2746 | 0.0337 | 0.0741 | 1.2180 | 0.0207 | 0.3299 | 72 |
123
+ | 0.2549 | 0.0339 | 0.0705 | 1.2496 | 0.0206 | 0.3308 | 73 |
124
+ | 0.2529 | 0.0339 | 0.0685 | 1.2239 | 0.0207 | 0.3321 | 74 |
125
+ | 0.2427 | 0.0340 | 0.0671 | 1.2351 | 0.0207 | 0.3292 | 75 |
126
+ | 0.2166 | 0.0343 | 0.0623 | 1.2361 | 0.0207 | 0.3313 | 76 |
127
+ | 0.2030 | 0.0345 | 0.0585 | 1.2462 | 0.0207 | 0.3312 | 77 |
128
+ | 0.2126 | 0.0344 | 0.0566 | 1.2441 | 0.0207 | 0.3313 | 78 |
129
+ | 0.2166 | 0.0343 | 0.0569 | 1.2506 | 0.0207 | 0.3334 | 79 |
130
+ | 0.2088 | 0.0344 | 0.0562 | 1.2557 | 0.0207 | 0.3389 | 80 |
131
+ | 0.2212 | 0.0342 | 0.0560 | 1.2652 | 0.0207 | 0.3334 | 81 |
132
+ | 0.2256 | 0.0343 | 0.0543 | 1.2543 | 0.0207 | 0.3393 | 82 |
133
+ | 0.1915 | 0.0346 | 0.0501 | 1.2540 | 0.0207 | 0.3299 | 83 |
134
+ | 0.1544 | 0.0350 | 0.0443 | 1.2676 | 0.0207 | 0.3347 | 84 |
135
+ | 0.1567 | 0.0350 | 0.0435 | 1.2740 | 0.0207 | 0.3375 | 85 |
136
+ | 0.1329 | 0.0352 | 0.0405 | 1.2833 | 0.0207 | 0.3398 | 86 |
137
+ | 0.1261 | 0.0353 | 0.0392 | 1.3088 | 0.0206 | 0.3397 | 87 |
138
+ | 0.1547 | 0.0350 | 0.0438 | 1.2933 | 0.0207 | 0.3279 | 88 |
139
+ | 0.1288 | 0.0352 | 0.0377 | 1.2985 | 0.0208 | 0.3371 | 89 |
140
+ | 0.1400 | 0.0351 | 0.0391 | 1.3020 | 0.0208 | 0.3329 | 90 |
141
+ | 0.1077 | 0.0355 | 0.0351 | 1.3118 | 0.0207 | 0.3344 | 91 |
142
+ | 0.0982 | 0.0355 | 0.0348 | 1.3274 | 0.0207 | 0.3352 | 92 |
143
+ | 0.1041 | 0.0355 | 0.0356 | 1.3251 | 0.0208 | 0.3362 | 93 |
144
+ | 0.1573 | 0.0350 | 0.0364 | 1.3173 | 0.0208 | 0.3362 | 94 |
145
+ | 0.1478 | 0.0350 | 0.0365 | 1.3125 | 0.0208 | 0.3367 | 95 |
146
+ | 0.0929 | 0.0356 | 0.0336 | 1.3256 | 0.0208 | 0.3351 | 96 |
147
+ | 0.1106 | 0.0354 | 0.0341 | 1.3289 | 0.0208 | 0.3428 | 97 |
148
+ | 0.0916 | 0.0355 | 0.0322 | 1.3384 | 0.0208 | 0.3383 | 98 |
149
+ | 0.0708 | 0.0358 | 0.0313 | 1.3525 | 0.0208 | 0.3333 | 99 |
150
+ | 0.1271 | 0.0352 | 0.0326 | 1.3447 | 0.0208 | 0.3336 | 100 |
151
+ | 0.0963 | 0.0355 | 0.0329 | 1.3481 | 0.0208 | 0.3288 | 101 |
152
+ | 0.0698 | 0.0358 | 0.0294 | 1.3748 | 0.0207 | 0.3341 | 102 |
153
+ | 0.0844 | 0.0356 | 0.0313 | 1.3615 | 0.0208 | 0.3380 | 103 |
154
+ | 0.1045 | 0.0354 | 0.0319 | 1.3519 | 0.0208 | 0.3357 | 104 |
155
+ | 0.0877 | 0.0355 | 0.0326 | 1.3760 | 0.0207 | 0.3402 | 105 |
156
+ | 0.0713 | 0.0357 | 0.0303 | 1.3742 | 0.0208 | 0.3392 | 106 |
157
+ | 0.0686 | 0.0358 | 0.0292 | 1.3920 | 0.0207 | 0.3353 | 107 |
158
+ | 0.0466 | 0.0360 | 0.0287 | 1.3964 | 0.0208 | 0.3342 | 108 |
159
+ | 0.0353 | 0.0361 | 0.0258 | 1.3977 | 0.0208 | 0.3339 | 109 |
160
+
161
+
162
+ ### Framework versions
163
+
164
+ - Transformers 4.33.0.dev0
165
+ - TensorFlow 2.13.0
166
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "init_std": 0.02,
29
+ "is_encoder_decoder": true,
30
+ "mask_feature_length": 10,
31
+ "mask_feature_min_masks": 0,
32
+ "mask_feature_prob": 0.0,
33
+ "mask_time_length": 10,
34
+ "mask_time_min_masks": 2,
35
+ "mask_time_prob": 0.05,
36
+ "max_length": 448,
37
+ "max_source_positions": 1500,
38
+ "max_target_positions": 448,
39
+ "median_filter_width": 7,
40
+ "model_type": "whisper",
41
+ "num_hidden_layers": 4,
42
+ "num_mel_bins": 80,
43
+ "pad_token_id": -100,
44
+ "scale_embedding": false,
45
+ "suppress_tokens": [],
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.33.0.dev0",
48
+ "use_cache": true,
49
+ "use_weighted_layer_sum": false,
50
+ "vocab_size": 51865
51
+ }
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 sha256:1b4bb13cf9225dee3bbaa433bdea3c30cb745b342f96b8151112be39ec803cbc
3
+ size 151253960