Hugging Face's logo

bigmorning
/
whisper_input_decoder_no_lob_with_force__0115

Automatic Speech Recognition
Transformers
TensorFlow
whisper
generated_from_keras_callback
Model card Files
xet
 Community
bigmorning commited on
Commit
1b709e0
·
1 Parent(s): c5e2872

Upload TFWhisperForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +171 -0
  2. config.json +64 -0
  3. generation_config.json +117 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_with_force__0115
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_with_force__0115
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: 0.0555
19
+ - Train Accuracy: 0.0359
20
+ - Train Wermet: 0.0109
21
+ - Validation Loss: 1.4518
22
+ - Validation Accuracy: 0.0206
23
+ - Validation Wermet: 0.3383
24
+ - Epoch: 114
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
+ | 5.4192 | 0.0107 | 1.1095 | 3.9799 | 0.0114 | 0.9502 | 0 |
51
+ | 4.7193 | 0.0116 | 0.8751 | 3.9335 | 0.0114 | 0.9414 | 1 |
52
+ | 4.6743 | 0.0117 | 0.8498 | 3.9949 | 0.0112 | 0.9682 | 2 |
53
+ | 4.6508 | 0.0117 | 0.8454 | 3.8900 | 0.0114 | 0.9453 | 3 |
54
+ | 4.6308 | 0.0118 | 0.8337 | 3.8853 | 0.0114 | 0.9495 | 4 |
55
+ | 4.6102 | 0.0118 | 0.8215 | 3.8884 | 0.0115 | 0.9205 | 5 |
56
+ | 4.5940 | 0.0118 | 0.8132 | 3.8409 | 0.0116 | 0.9007 | 6 |
57
+ | 4.5703 | 0.0119 | 0.7971 | 3.8224 | 0.0116 | 0.9098 | 7 |
58
+ | 4.5470 | 0.0120 | 0.7822 | 3.8013 | 0.0116 | 0.8938 | 8 |
59
+ | 4.5219 | 0.0120 | 0.7679 | 3.7776 | 0.0117 | 0.8829 | 9 |
60
+ | 4.4859 | 0.0121 | 0.7519 | 3.7360 | 0.0118 | 0.8411 | 10 |
61
+ | 4.4408 | 0.0123 | 0.7412 | 3.6972 | 0.0118 | 0.8593 | 11 |
62
+ | 4.3774 | 0.0124 | 0.7240 | 3.6035 | 0.0121 | 0.8234 | 12 |
63
+ | 4.2906 | 0.0127 | 0.7168 | 3.5057 | 0.0123 | 0.8130 | 13 |
64
+ | 4.1748 | 0.0130 | 0.7090 | 3.3528 | 0.0127 | 0.7856 | 14 |
65
+ | 4.0214 | 0.0135 | 0.7048 | 3.2086 | 0.0130 | 0.7786 | 15 |
66
+ | 3.8434 | 0.0140 | 0.6918 | 3.0436 | 0.0134 | 0.7466 | 16 |
67
+ | 3.6564 | 0.0146 | 0.6797 | 2.8693 | 0.0138 | 0.7348 | 17 |
68
+ | 3.4565 | 0.0152 | 0.6658 | 2.6967 | 0.0143 | 0.7131 | 18 |
69
+ | 3.2849 | 0.0158 | 0.6496 | 2.5221 | 0.0148 | 0.6792 | 19 |
70
+ | 3.0761 | 0.0165 | 0.6273 | 2.3796 | 0.0153 | 0.6550 | 20 |
71
+ | 2.9131 | 0.0171 | 0.6028 | 2.2468 | 0.0156 | 0.6282 | 21 |
72
+ | 2.7468 | 0.0178 | 0.5812 | 2.1322 | 0.0160 | 0.6123 | 22 |
73
+ | 2.6133 | 0.0183 | 0.5606 | 2.1131 | 0.0160 | 0.5950 | 23 |
74
+ | 2.4732 | 0.0189 | 0.5367 | 2.0006 | 0.0164 | 0.5730 | 24 |
75
+ | 2.3339 | 0.0196 | 0.5164 | 1.8895 | 0.0168 | 0.5532 | 25 |
76
+ | 2.2300 | 0.0200 | 0.4985 | 1.8183 | 0.0172 | 0.5430 | 26 |
77
+ | 2.1215 | 0.0206 | 0.4787 | 1.7413 | 0.0174 | 0.5230 | 27 |
78
+ | 2.0359 | 0.0210 | 0.4608 | 1.6732 | 0.0177 | 0.5099 | 28 |
79
+ | 1.9219 | 0.0216 | 0.4433 | 1.6287 | 0.0179 | 0.4979 | 29 |
80
+ | 1.8477 | 0.0220 | 0.4274 | 1.6129 | 0.0180 | 0.4896 | 30 |
81
+ | 1.7778 | 0.0224 | 0.4123 | 1.5705 | 0.0182 | 0.4769 | 31 |
82
+ | 1.6924 | 0.0228 | 0.3980 | 1.5096 | 0.0185 | 0.4666 | 32 |
83
+ | 1.6389 | 0.0231 | 0.3847 | 1.4837 | 0.0186 | 0.4558 | 33 |
84
+ | 1.5687 | 0.0235 | 0.3710 | 1.4419 | 0.0188 | 0.4475 | 34 |
85
+ | 1.4742 | 0.0242 | 0.3566 | 1.4365 | 0.0188 | 0.4385 | 35 |
86
+ | 1.4321 | 0.0244 | 0.3452 | 1.4011 | 0.0190 | 0.4300 | 36 |
87
+ | 1.3712 | 0.0248 | 0.3328 | 1.4145 | 0.0189 | 0.4245 | 37 |
88
+ | 1.3249 | 0.0251 | 0.3231 | 1.3604 | 0.0192 | 0.4188 | 38 |
89
+ | 1.2787 | 0.0253 | 0.3113 | 1.3424 | 0.0193 | 0.4133 | 39 |
90
+ | 1.1978 | 0.0259 | 0.2997 | 1.3275 | 0.0194 | 0.4068 | 40 |
91
+ | 1.1643 | 0.0261 | 0.2893 | 1.3122 | 0.0195 | 0.4019 | 41 |
92
+ | 1.1043 | 0.0266 | 0.2785 | 1.3011 | 0.0195 | 0.3964 | 42 |
93
+ | 1.0828 | 0.0267 | 0.2712 | 1.3235 | 0.0195 | 0.3932 | 43 |
94
+ | 1.0231 | 0.0272 | 0.2601 | 1.2947 | 0.0196 | 0.3873 | 44 |
95
+ | 0.9817 | 0.0275 | 0.2511 | 1.2785 | 0.0198 | 0.3855 | 45 |
96
+ | 0.9612 | 0.0276 | 0.2430 | 1.2755 | 0.0198 | 0.3831 | 46 |
97
+ | 0.9191 | 0.0280 | 0.2330 | 1.2522 | 0.0199 | 0.3744 | 47 |
98
+ | 0.8629 | 0.0284 | 0.2234 | 1.2679 | 0.0199 | 0.3759 | 48 |
99
+ | 0.8454 | 0.0285 | 0.2159 | 1.2575 | 0.0199 | 0.3732 | 49 |
100
+ | 0.7928 | 0.0290 | 0.2064 | 1.2505 | 0.0200 | 0.3693 | 50 |
101
+ | 0.7814 | 0.0291 | 0.2003 | 1.2450 | 0.0200 | 0.3669 | 51 |
102
+ | 0.7775 | 0.0291 | 0.1948 | 1.2965 | 0.0198 | 0.3662 | 52 |
103
+ | 0.7274 | 0.0295 | 0.1858 | 1.2472 | 0.0201 | 0.3663 | 53 |
104
+ | 0.7132 | 0.0296 | 0.1787 | 1.2389 | 0.0201 | 0.3591 | 54 |
105
+ | 0.6941 | 0.0298 | 0.1731 | 1.2386 | 0.0201 | 0.3564 | 55 |
106
+ | 0.6327 | 0.0304 | 0.1633 | 1.2437 | 0.0201 | 0.3557 | 56 |
107
+ | 0.6090 | 0.0306 | 0.1569 | 1.2333 | 0.0202 | 0.3532 | 57 |
108
+ | 0.6347 | 0.0303 | 0.1561 | 1.2425 | 0.0202 | 0.3564 | 58 |
109
+ | 0.5639 | 0.0310 | 0.1447 | 1.2261 | 0.0202 | 0.3526 | 59 |
110
+ | 0.5470 | 0.0311 | 0.1383 | 1.2476 | 0.0202 | 0.3497 | 60 |
111
+ | 0.5209 | 0.0314 | 0.1324 | 1.2304 | 0.0203 | 0.3489 | 61 |
112
+ | 0.5326 | 0.0313 | 0.1300 | 1.2410 | 0.0203 | 0.3482 | 62 |
113
+ | 0.5106 | 0.0314 | 0.1236 | 1.2508 | 0.0203 | 0.3462 | 63 |
114
+ | 0.4984 | 0.0315 | 0.1197 | 1.2628 | 0.0202 | 0.3489 | 64 |
115
+ | 0.4676 | 0.0319 | 0.1129 | 1.2352 | 0.0204 | 0.3446 | 65 |
116
+ | 0.4612 | 0.0319 | 0.1091 | 1.2369 | 0.0204 | 0.3441 | 66 |
117
+ | 0.4367 | 0.0321 | 0.1030 | 1.2393 | 0.0204 | 0.3440 | 67 |
118
+ | 0.4165 | 0.0323 | 0.0984 | 1.2412 | 0.0204 | 0.3413 | 68 |
119
+ | 0.4154 | 0.0323 | 0.0955 | 1.2445 | 0.0204 | 0.3423 | 69 |
120
+ | 0.4130 | 0.0323 | 0.0922 | 1.2361 | 0.0205 | 0.3408 | 70 |
121
+ | 0.3758 | 0.0327 | 0.0857 | 1.2439 | 0.0204 | 0.3406 | 71 |
122
+ | 0.3566 | 0.0329 | 0.0812 | 1.2406 | 0.0205 | 0.3392 | 72 |
123
+ | 0.3232 | 0.0333 | 0.0750 | 1.2572 | 0.0205 | 0.3386 | 73 |
124
+ | 0.3755 | 0.0327 | 0.0776 | 1.2465 | 0.0205 | 0.3372 | 74 |
125
+ | 0.3485 | 0.0330 | 0.0733 | 1.2488 | 0.0205 | 0.3366 | 75 |
126
+ | 0.2972 | 0.0335 | 0.0651 | 1.2797 | 0.0204 | 0.3408 | 76 |
127
+ | 0.3179 | 0.0334 | 0.0649 | 1.2714 | 0.0205 | 0.3368 | 77 |
128
+ | 0.2738 | 0.0338 | 0.0579 | 1.2693 | 0.0205 | 0.3384 | 78 |
129
+ | 0.2658 | 0.0339 | 0.0544 | 1.2769 | 0.0205 | 0.3385 | 79 |
130
+ | 0.2337 | 0.0342 | 0.0493 | 1.2862 | 0.0205 | 0.3363 | 80 |
131
+ | 0.2667 | 0.0338 | 0.0513 | 1.2851 | 0.0205 | 0.3379 | 81 |
132
+ | 0.2639 | 0.0338 | 0.0488 | 1.2911 | 0.0205 | 0.3382 | 82 |
133
+ | 0.2682 | 0.0338 | 0.0498 | 1.2893 | 0.0205 | 0.3370 | 83 |
134
+ | 0.2325 | 0.0341 | 0.0442 | 1.2965 | 0.0205 | 0.3380 | 84 |
135
+ | 0.2534 | 0.0339 | 0.0452 | 1.2888 | 0.0205 | 0.3366 | 85 |
136
+ | 0.2503 | 0.0340 | 0.0429 | 1.3043 | 0.0205 | 0.3373 | 86 |
137
+ | 0.1962 | 0.0346 | 0.0367 | 1.3363 | 0.0205 | 0.3396 | 87 |
138
+ | 0.1735 | 0.0348 | 0.0329 | 1.3139 | 0.0205 | 0.3372 | 88 |
139
+ | 0.1664 | 0.0349 | 0.0316 | 1.3461 | 0.0204 | 0.3397 | 89 |
140
+ | 0.1891 | 0.0346 | 0.0335 | 1.3275 | 0.0206 | 0.3378 | 90 |
141
+ | 0.2370 | 0.0343 | 0.0369 | 1.3073 | 0.0206 | 0.3356 | 91 |
142
+ | 0.2429 | 0.0341 | 0.0380 | 1.3116 | 0.0205 | 0.3351 | 92 |
143
+ | 0.1635 | 0.0349 | 0.0272 | 1.3342 | 0.0205 | 0.3385 | 93 |
144
+ | 0.1326 | 0.0352 | 0.0235 | 1.3294 | 0.0206 | 0.3370 | 94 |
145
+ | 0.1322 | 0.0352 | 0.0224 | 1.3418 | 0.0206 | 0.3357 | 95 |
146
+ | 0.1357 | 0.0352 | 0.0224 | 1.3476 | 0.0206 | 0.3372 | 96 |
147
+ | 0.1394 | 0.0351 | 0.0230 | 1.3578 | 0.0206 | 0.3364 | 97 |
148
+ | 0.1370 | 0.0351 | 0.0224 | 1.3559 | 0.0206 | 0.3366 | 98 |
149
+ | 0.1700 | 0.0349 | 0.0259 | 1.3587 | 0.0205 | 0.3371 | 99 |
150
+ | 0.1102 | 0.0354 | 0.0183 | 1.3664 | 0.0206 | 0.3364 | 100 |
151
+ | 0.1039 | 0.0355 | 0.0175 | 1.4739 | 0.0203 | 0.3433 | 101 |
152
+ | 0.1094 | 0.0354 | 0.0184 | 1.3800 | 0.0206 | 0.3378 | 102 |
153
+ | 0.1426 | 0.0350 | 0.0203 | 1.3797 | 0.0206 | 0.3370 | 103 |
154
+ | 0.1132 | 0.0353 | 0.0175 | 1.4130 | 0.0205 | 0.3384 | 104 |
155
+ | 0.1029 | 0.0354 | 0.0160 | 1.4131 | 0.0205 | 0.3381 | 105 |
156
+ | 0.1241 | 0.0352 | 0.0183 | 1.3905 | 0.0206 | 0.3361 | 106 |
157
+ | 0.0869 | 0.0356 | 0.0133 | 1.4050 | 0.0206 | 0.3369 | 107 |
158
+ | 0.0805 | 0.0356 | 0.0138 | 1.4236 | 0.0206 | 0.3361 | 108 |
159
+ | 0.0842 | 0.0357 | 0.0154 | 1.4232 | 0.0206 | 0.3348 | 109 |
160
+ | 0.0567 | 0.0359 | 0.0106 | 1.4349 | 0.0206 | 0.3367 | 110 |
161
+ | 0.1302 | 0.0353 | 0.0205 | 1.4065 | 0.0206 | 0.3344 | 111 |
162
+ | 0.0802 | 0.0357 | 0.0130 | 1.4117 | 0.0206 | 0.3343 | 112 |
163
+ | 0.0541 | 0.0359 | 0.0116 | 1.4502 | 0.0206 | 0.3387 | 113 |
164
+ | 0.0555 | 0.0359 | 0.0109 | 1.4518 | 0.0206 | 0.3383 | 114 |
165
+
166
+
167
+ ### Framework versions
168
+
169
+ - Transformers 4.33.0.dev0
170
+ - TensorFlow 2.13.0
171
+ - 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": -100,
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:d692b5122e28cf882e40d611f409842b42078b5c14f3bb37c2d22fc3bf5c1f79
3
+ size 151253960