Hugging Face's logo

bigmorning
/
whisper_char_cv12_pad_lob100_low__0075

Automatic Speech Recognition
Transformers
TensorFlow
whisper
generated_from_keras_callback
Inference Endpoints
Model card Files Community
bigmorning commited on
Commit
058ca7d
•
1 Parent(s): 5ba5aa4

Upload TFWhisperForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +131 -0
  2. config.json +64 -0
  3. generation_config.json +117 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_char_cv12_pad_lob100_low__0075
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_char_cv12_pad_lob100_low__0075
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: 0.0075
19
+ - Train Accuracy: 0.1113
20
+ - Train Wermet: 3.5938
21
+ - Validation Loss: 0.5416
22
+ - Validation Accuracy: 0.0639
23
+ - Validation Wermet: 10.3651
24
+ - Epoch: 74
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
+ | 0.3330 | 0.0999 | 1.7359 | 0.3779 | 0.0615 | 4.7471 | 0 |
51
+ | 0.3093 | 0.1007 | 2.0563 | 0.3652 | 0.0618 | 7.2181 | 1 |
52
+ | 0.2869 | 0.1015 | 2.0654 | 0.3539 | 0.0620 | 8.6857 | 2 |
53
+ | 0.2672 | 0.1022 | 2.1925 | 0.3443 | 0.0623 | 8.0906 | 3 |
54
+ | 0.2488 | 0.1028 | 2.3286 | 0.3305 | 0.0626 | 9.1756 | 4 |
55
+ | 0.2316 | 0.1034 | 2.4212 | 0.3300 | 0.0626 | 8.1427 | 5 |
56
+ | 0.2163 | 0.1039 | 2.5012 | 0.3183 | 0.0629 | 8.3043 | 6 |
57
+ | 0.2018 | 0.1045 | 2.7267 | 0.3109 | 0.0631 | 9.5329 | 7 |
58
+ | 0.1878 | 0.1050 | 2.7034 | 0.3053 | 0.0632 | 7.9014 | 8 |
59
+ | 0.1749 | 0.1054 | 2.8719 | 0.3063 | 0.0632 | 9.0257 | 9 |
60
+ | 0.1628 | 0.1058 | 2.8764 | 0.3033 | 0.0634 | 9.1336 | 10 |
61
+ | 0.1510 | 0.1063 | 2.8441 | 0.3046 | 0.0634 | 8.6064 | 11 |
62
+ | 0.1391 | 0.1067 | 2.9377 | 0.3030 | 0.0635 | 9.1326 | 12 |
63
+ | 0.1280 | 0.1071 | 2.9433 | 0.3025 | 0.0636 | 9.4533 | 13 |
64
+ | 0.1182 | 0.1075 | 3.1399 | 0.3076 | 0.0636 | 9.9836 | 14 |
65
+ | 0.1086 | 0.1078 | 3.2411 | 0.3096 | 0.0636 | 8.8470 | 15 |
66
+ | 0.0983 | 0.1082 | 3.2622 | 0.3125 | 0.0636 | 9.1506 | 16 |
67
+ | 0.0889 | 0.1086 | 3.3368 | 0.3184 | 0.0636 | 8.9635 | 17 |
68
+ | 0.0803 | 0.1089 | 3.2742 | 0.3204 | 0.0637 | 9.3550 | 18 |
69
+ | 0.0720 | 0.1092 | 3.4052 | 0.3258 | 0.0637 | 10.1082 | 19 |
70
+ | 0.0637 | 0.1096 | 3.4287 | 0.3342 | 0.0637 | 10.3977 | 20 |
71
+ | 0.0566 | 0.1098 | 3.4708 | 0.3411 | 0.0636 | 10.6479 | 21 |
72
+ | 0.0498 | 0.1101 | 3.4462 | 0.3463 | 0.0637 | 10.1602 | 22 |
73
+ | 0.0429 | 0.1104 | 3.4056 | 0.3588 | 0.0636 | 9.7172 | 23 |
74
+ | 0.0374 | 0.1106 | 3.4477 | 0.3656 | 0.0636 | 9.4476 | 24 |
75
+ | 0.0325 | 0.1108 | 3.4474 | 0.3712 | 0.0637 | 9.6926 | 25 |
76
+ | 0.0279 | 0.1109 | 3.4263 | 0.3836 | 0.0636 | 10.0768 | 26 |
77
+ | 0.0233 | 0.1111 | 3.4779 | 0.3873 | 0.0637 | 9.8123 | 27 |
78
+ | 0.0196 | 0.1112 | 3.5329 | 0.4015 | 0.0636 | 10.0477 | 28 |
79
+ | 0.0160 | 0.1113 | 3.5049 | 0.4097 | 0.0636 | 10.4027 | 29 |
80
+ | 0.0139 | 0.1114 | 3.6185 | 0.4201 | 0.0636 | 10.9904 | 30 |
81
+ | 0.0112 | 0.1114 | 3.5812 | 0.4300 | 0.0636 | 10.4501 | 31 |
82
+ | 0.0096 | 0.1115 | 3.7493 | 0.4409 | 0.0636 | 10.3964 | 32 |
83
+ | 0.0089 | 0.1115 | 3.6912 | 0.4499 | 0.0636 | 10.8345 | 33 |
84
+ | 0.0082 | 0.1115 | 3.7577 | 0.4583 | 0.0636 | 10.2883 | 34 |
85
+ | 0.0090 | 0.1114 | 3.8468 | 0.4755 | 0.0635 | 11.8086 | 35 |
86
+ | 0.0168 | 0.1111 | 3.6340 | 0.4592 | 0.0636 | 10.6373 | 36 |
87
+ | 0.0072 | 0.1115 | 3.8163 | 0.4644 | 0.0637 | 10.2448 | 37 |
88
+ | 0.0040 | 0.1115 | 3.8376 | 0.4728 | 0.0637 | 10.9074 | 38 |
89
+ | 0.0029 | 0.1115 | 3.8274 | 0.4814 | 0.0637 | 10.5440 | 39 |
90
+ | 0.0025 | 0.1115 | 3.8022 | 0.4891 | 0.0637 | 10.8606 | 40 |
91
+ | 0.0021 | 0.1115 | 3.8940 | 0.4937 | 0.0637 | 10.9388 | 41 |
92
+ | 0.0018 | 0.1115 | 3.8026 | 0.5030 | 0.0637 | 10.6511 | 42 |
93
+ | 0.0014 | 0.1115 | 3.8260 | 0.5092 | 0.0637 | 10.5743 | 43 |
94
+ | 0.0173 | 0.1110 | 3.6223 | 0.5066 | 0.0635 | 9.9370 | 44 |
95
+ | 0.0073 | 0.1114 | 3.6868 | 0.4972 | 0.0637 | 10.6775 | 45 |
96
+ | 0.0027 | 0.1115 | 3.6742 | 0.5025 | 0.0638 | 10.3476 | 46 |
97
+ | 0.0016 | 0.1115 | 3.7677 | 0.5078 | 0.0638 | 10.2277 | 47 |
98
+ | 0.0013 | 0.1115 | 3.7721 | 0.5131 | 0.0638 | 10.4473 | 48 |
99
+ | 0.0011 | 0.1115 | 3.8394 | 0.5189 | 0.0638 | 10.4344 | 49 |
100
+ | 0.0009 | 0.1116 | 3.8666 | 0.5245 | 0.0638 | 10.4933 | 50 |
101
+ | 0.0008 | 0.1116 | 3.8432 | 0.5307 | 0.0638 | 10.5118 | 51 |
102
+ | 0.0008 | 0.1115 | 3.8808 | 0.5391 | 0.0637 | 10.7086 | 52 |
103
+ | 0.0207 | 0.1108 | 3.8324 | 0.5204 | 0.0636 | 9.3724 | 53 |
104
+ | 0.0074 | 0.1113 | 3.4605 | 0.5254 | 0.0637 | 10.1335 | 54 |
105
+ | 0.0023 | 0.1115 | 3.6304 | 0.5164 | 0.0639 | 10.2554 | 55 |
106
+ | 0.0012 | 0.1115 | 3.7309 | 0.5202 | 0.0639 | 10.3892 | 56 |
107
+ | 0.0009 | 0.1115 | 3.6945 | 0.5260 | 0.0639 | 10.0808 | 57 |
108
+ | 0.0007 | 0.1116 | 3.6804 | 0.5308 | 0.0639 | 10.2385 | 58 |
109
+ | 0.0006 | 0.1116 | 3.6696 | 0.5350 | 0.0639 | 10.1248 | 59 |
110
+ | 0.0005 | 0.1116 | 3.7425 | 0.5394 | 0.0639 | 10.1711 | 60 |
111
+ | 0.0005 | 0.1116 | 3.7317 | 0.5442 | 0.0639 | 10.1407 | 61 |
112
+ | 0.0004 | 0.1116 | 3.7010 | 0.5490 | 0.0639 | 10.0544 | 62 |
113
+ | 0.0004 | 0.1116 | 3.6921 | 0.5546 | 0.0639 | 10.1746 | 63 |
114
+ | 0.0003 | 0.1116 | 3.7494 | 0.5598 | 0.0639 | 10.0562 | 64 |
115
+ | 0.0025 | 0.1115 | 3.6924 | 0.6395 | 0.0628 | 8.8622 | 65 |
116
+ | 0.0189 | 0.1109 | 3.7101 | 0.5363 | 0.0638 | 11.1245 | 66 |
117
+ | 0.0035 | 0.1115 | 3.6989 | 0.5347 | 0.0639 | 11.3329 | 67 |
118
+ | 0.0012 | 0.1115 | 3.6723 | 0.5407 | 0.0639 | 11.2559 | 68 |
119
+ | 0.0007 | 0.1115 | 3.6834 | 0.5429 | 0.0639 | 11.0248 | 69 |
120
+ | 0.0006 | 0.1115 | 3.6848 | 0.5459 | 0.0639 | 10.8372 | 70 |
121
+ | 0.0005 | 0.1115 | 3.6407 | 0.5501 | 0.0639 | 10.9252 | 71 |
122
+ | 0.0005 | 0.1115 | 3.7172 | 0.5565 | 0.0639 | 10.6965 | 72 |
123
+ | 0.0123 | 0.1112 | 3.5604 | 0.5734 | 0.0635 | 10.3309 | 73 |
124
+ | 0.0075 | 0.1113 | 3.5938 | 0.5416 | 0.0639 | 10.3651 | 74 |
125
+
126
+
127
+ ### Framework versions
128
+
129
+ - Transformers 4.33.0.dev0
130
+ - TensorFlow 2.13.0
131
+ - 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 sha256:765c089cb5a8ec3e5d672ee0a8e52540bad1af2908ed621d28dbc345bb695c20
3
+ size 151253960