Hugging Face's logo

bigmorning
/
whisper_4_with_init_sun_char_0070

Automatic Speech Recognition
Transformers
TensorFlow
whisper
generated_from_keras_callback
Inference Endpoints
Model card Files Community
bigmorning commited on
Commit
25a7a40
•
1 Parent(s): 7926a12

Upload TFWhisperForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +126 -0
  2. config.json +64 -0
  3. generation_config.json +117 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_4_with_init_sun_char_0070
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_4_with_init_sun_char_0070
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: 1.3321
19
+ - Train Accuracy: 0.0587
20
+ - Train Wermet: 0.3546
21
+ - Validation Loss: 2.1066
22
+ - Validation Accuracy: 0.0314
23
+ - Validation Wermet: 0.6181
24
+ - Epoch: 69
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
+ | 3.2071 | 0.0313 | 0.1237 | 2.8546 | 0.0225 | 0.1109 | 0 |
51
+ | 3.0365 | 0.0325 | 0.0375 | 2.8115 | 0.0228 | 0.1215 | 1 |
52
+ | 3.0162 | 0.0326 | 0.0484 | 2.7884 | 0.0231 | 0.1318 | 2 |
53
+ | 3.0042 | 0.0327 | 0.0555 | 2.7853 | 0.0233 | 0.1393 | 3 |
54
+ | 2.9934 | 0.0328 | 0.0614 | 2.7657 | 0.0232 | 0.1273 | 4 |
55
+ | 2.9858 | 0.0329 | 0.0654 | 2.7542 | 0.0234 | 0.1073 | 5 |
56
+ | 2.9735 | 0.0330 | 0.0673 | 2.7367 | 0.0234 | 0.1414 | 6 |
57
+ | 2.9574 | 0.0332 | 0.0704 | 2.6961 | 0.0240 | 0.1429 | 7 |
58
+ | 2.9320 | 0.0335 | 0.0723 | 2.6652 | 0.0239 | 0.0990 | 8 |
59
+ | 2.8976 | 0.0339 | 0.0729 | 2.5997 | 0.0245 | 0.0944 | 9 |
60
+ | 2.8460 | 0.0343 | 0.0728 | 2.5378 | 0.0248 | 0.1435 | 10 |
61
+ | 2.7781 | 0.0347 | 0.0741 | 2.4355 | 0.0254 | 0.1372 | 11 |
62
+ | 2.7083 | 0.0352 | 0.0747 | 2.5163 | 0.0248 | 0.0987 | 12 |
63
+ | 2.6445 | 0.0356 | 0.0720 | 2.2997 | 0.0261 | 0.1484 | 13 |
64
+ | 2.5838 | 0.0360 | 0.0724 | 2.2386 | 0.0266 | 0.1419 | 14 |
65
+ | 2.5294 | 0.0363 | 0.0721 | 2.1855 | 0.0269 | 0.1289 | 15 |
66
+ | 2.4760 | 0.0367 | 0.0711 | 2.1682 | 0.0271 | 0.1214 | 16 |
67
+ | 2.4339 | 0.0370 | 0.0698 | 2.1018 | 0.0273 | 0.1264 | 17 |
68
+ | 2.3867 | 0.0373 | 0.0684 | 2.0647 | 0.0275 | 0.1403 | 18 |
69
+ | 2.3528 | 0.0376 | 0.0669 | 2.0705 | 0.0275 | 0.1089 | 19 |
70
+ | 2.3145 | 0.0379 | 0.0658 | 2.0179 | 0.0280 | 0.1209 | 20 |
71
+ | 2.2765 | 0.0382 | 0.0654 | 2.0182 | 0.0279 | 0.1023 | 21 |
72
+ | 2.2415 | 0.0385 | 0.0650 | 1.9558 | 0.0284 | 0.1523 | 22 |
73
+ | 2.2102 | 0.0388 | 0.0643 | 1.9395 | 0.0285 | 0.1123 | 23 |
74
+ | 2.1717 | 0.0392 | 0.0635 | 1.9791 | 0.0282 | 0.0928 | 24 |
75
+ | 2.1457 | 0.0395 | 0.0626 | 1.8907 | 0.0291 | 0.1078 | 25 |
76
+ | 2.1159 | 0.0398 | 0.0633 | 1.8930 | 0.0290 | 0.1098 | 26 |
77
+ | 2.0892 | 0.0401 | 0.0638 | 1.8696 | 0.0292 | 0.1078 | 27 |
78
+ | 2.0609 | 0.0405 | 0.0659 | 1.8555 | 0.0296 | 0.1051 | 28 |
79
+ | 2.0342 | 0.0409 | 0.0639 | 1.8589 | 0.0293 | 0.1092 | 29 |
80
+ | 2.0044 | 0.0413 | 0.0653 | 1.8375 | 0.0299 | 0.1015 | 30 |
81
+ | 1.9831 | 0.0416 | 0.0649 | 1.7954 | 0.0302 | 0.1194 | 31 |
82
+ | 1.9535 | 0.0421 | 0.0689 | 1.7937 | 0.0302 | 0.1168 | 32 |
83
+ | 1.9290 | 0.0425 | 0.0706 | 1.8385 | 0.0299 | 0.1074 | 33 |
84
+ | 1.8933 | 0.0432 | 0.0682 | 1.8761 | 0.0295 | 0.1173 | 34 |
85
+ | 1.8724 | 0.0435 | 0.0752 | 1.7929 | 0.0304 | 0.1220 | 35 |
86
+ | 1.8407 | 0.0442 | 0.0760 | 1.7865 | 0.0306 | 0.1266 | 36 |
87
+ | 1.8179 | 0.0446 | 0.0832 | 1.8108 | 0.0304 | 0.1226 | 37 |
88
+ | 1.7977 | 0.0451 | 0.0888 | 1.8024 | 0.0306 | 0.1161 | 38 |
89
+ | 1.7846 | 0.0454 | 0.0855 | 1.8107 | 0.0305 | 0.1385 | 39 |
90
+ | 1.7516 | 0.0461 | 0.0922 | 1.8258 | 0.0307 | 0.1365 | 40 |
91
+ | 1.7358 | 0.0465 | 0.1070 | 1.8837 | 0.0302 | 0.1461 | 41 |
92
+ | 1.7036 | 0.0474 | 0.1106 | 1.8589 | 0.0306 | 0.1201 | 42 |
93
+ | 1.6779 | 0.0481 | 0.1052 | 1.8831 | 0.0305 | 0.1755 | 43 |
94
+ | 1.6539 | 0.0487 | 0.1192 | 1.8249 | 0.0309 | 0.1901 | 44 |
95
+ | 1.6500 | 0.0488 | 0.1149 | 1.8435 | 0.0310 | 0.1313 | 45 |
96
+ | 1.6401 | 0.0490 | 0.1468 | 1.8509 | 0.0310 | 0.1597 | 46 |
97
+ | 1.6232 | 0.0495 | 0.1443 | 1.8573 | 0.0310 | 0.1588 | 47 |
98
+ | 1.5947 | 0.0503 | 0.1315 | 1.8350 | 0.0311 | 0.1476 | 48 |
99
+ | 1.5659 | 0.0512 | 0.1890 | 1.8934 | 0.0310 | 0.1507 | 49 |
100
+ | 1.5409 | 0.0521 | 0.1410 | 1.9782 | 0.0299 | 0.1663 | 50 |
101
+ | 1.5417 | 0.0520 | 0.1805 | 1.9223 | 0.0309 | 0.2287 | 51 |
102
+ | 1.5330 | 0.0522 | 0.1907 | 1.9174 | 0.0313 | 0.2481 | 52 |
103
+ | 1.5182 | 0.0527 | 0.1963 | 1.9254 | 0.0312 | 0.1440 | 53 |
104
+ | 1.5008 | 0.0532 | 0.2386 | 1.9368 | 0.0309 | 0.2045 | 54 |
105
+ | 1.4700 | 0.0543 | 0.2347 | 1.9171 | 0.0310 | 0.3189 | 55 |
106
+ | 1.4517 | 0.0549 | 0.2159 | 1.9880 | 0.0308 | 0.4000 | 56 |
107
+ | 1.4421 | 0.0553 | 0.2616 | 1.9647 | 0.0310 | 0.3311 | 57 |
108
+ | 1.4393 | 0.0552 | 0.2959 | 1.9191 | 0.0314 | 0.3403 | 58 |
109
+ | 1.4163 | 0.0560 | 0.3296 | 2.0068 | 0.0313 | 0.3711 | 59 |
110
+ | 1.4174 | 0.0559 | 0.3499 | 2.0338 | 0.0310 | 0.2981 | 60 |
111
+ | 1.4112 | 0.0561 | 0.3553 | 2.0262 | 0.0312 | 0.3595 | 61 |
112
+ | 1.3840 | 0.0572 | 0.4110 | 1.9913 | 0.0313 | 0.2975 | 62 |
113
+ | 1.3662 | 0.0578 | 0.3471 | 2.0969 | 0.0307 | 0.2794 | 63 |
114
+ | 1.3596 | 0.0579 | 0.3211 | 2.0164 | 0.0314 | 0.9982 | 64 |
115
+ | 1.3819 | 0.0571 | 0.3542 | 1.9052 | 0.0315 | 0.9802 | 65 |
116
+ | 1.3823 | 0.0569 | 0.3757 | 1.9371 | 0.0315 | 1.0860 | 66 |
117
+ | 1.3364 | 0.0587 | 0.4048 | 2.0912 | 0.0311 | 0.2807 | 67 |
118
+ | 1.3494 | 0.0582 | 0.3723 | 1.9475 | 0.0317 | 0.3295 | 68 |
119
+ | 1.3321 | 0.0587 | 0.3546 | 2.1066 | 0.0314 | 0.6181 | 69 |
120
+
121
+
122
+ ### Framework versions
123
+
124
+ - Transformers 4.34.0.dev0
125
+ - TensorFlow 2.13.0
126
+ - 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": "4.34.0.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": "4.34.0.dev0"
117
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c04bb4a9cae19459963c320170829280f3ab6238b40d22f3086e40750d32ebc
3
+ size 151253960