Hugging Face's logo

bigmorning
/
whisper_charsplit_new_0078

Automatic Speech Recognition
Transformers
TensorFlow
whisper
generated_from_keras_callback
Inference Endpoints
Model card Files Community
bigmorning commited on
Commit
71fb9d1
•
1 Parent(s): de3c9e2

Upload TFWhisperForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +134 -0
  2. config.json +64 -0
  3. generation_config.json +117 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_charsplit_new_0078
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_charsplit_new_0078
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: 0.0006
19
+ - Train Accuracy: 0.0795
20
+ - Train Wermet: 10.1888
21
+ - Validation Loss: 0.5371
22
+ - Validation Accuracy: 0.0767
23
+ - Validation Wermet: 8.9689
24
+ - Epoch: 77
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
+ | 0.8733 | 0.0602 | 13.0686 | 0.6470 | 0.0676 | 11.4066 | 0 |
51
+ | 0.5740 | 0.0666 | 12.7778 | 0.5113 | 0.0706 | 11.1022 | 1 |
52
+ | 0.4553 | 0.0692 | 12.2404 | 0.4371 | 0.0723 | 10.9105 | 2 |
53
+ | 0.3813 | 0.0708 | 11.9157 | 0.3935 | 0.0733 | 9.4615 | 3 |
54
+ | 0.3292 | 0.0720 | 11.5732 | 0.3630 | 0.0740 | 9.9885 | 4 |
55
+ | 0.2886 | 0.0729 | 11.5171 | 0.3403 | 0.0745 | 9.8042 | 5 |
56
+ | 0.2561 | 0.0736 | 11.3173 | 0.3256 | 0.0749 | 9.9431 | 6 |
57
+ | 0.2282 | 0.0743 | 11.7308 | 0.3159 | 0.0752 | 9.2086 | 7 |
58
+ | 0.2036 | 0.0748 | 11.4503 | 0.3071 | 0.0754 | 9.5236 | 8 |
59
+ | 0.1820 | 0.0754 | 11.7175 | 0.3005 | 0.0756 | 10.0755 | 9 |
60
+ | 0.1628 | 0.0758 | 11.7056 | 0.2993 | 0.0757 | 9.9497 | 10 |
61
+ | 0.1450 | 0.0762 | 11.7637 | 0.2971 | 0.0758 | 10.1481 | 11 |
62
+ | 0.1287 | 0.0766 | 11.8509 | 0.3029 | 0.0759 | 10.2042 | 12 |
63
+ | 0.1140 | 0.0770 | 12.1100 | 0.3004 | 0.0760 | 10.3873 | 13 |
64
+ | 0.0998 | 0.0773 | 11.9502 | 0.3025 | 0.0761 | 10.7066 | 14 |
65
+ | 0.0872 | 0.0777 | 12.3196 | 0.3129 | 0.0759 | 10.7707 | 15 |
66
+ | 0.0760 | 0.0779 | 12.2637 | 0.3142 | 0.0761 | 10.2638 | 16 |
67
+ | 0.0651 | 0.0782 | 12.1215 | 0.3192 | 0.0761 | 10.0750 | 17 |
68
+ | 0.0547 | 0.0785 | 12.0551 | 0.3294 | 0.0761 | 10.4732 | 18 |
69
+ | 0.0463 | 0.0787 | 11.9677 | 0.3402 | 0.0760 | 10.2814 | 19 |
70
+ | 0.0386 | 0.0789 | 11.6855 | 0.3517 | 0.0760 | 10.0599 | 20 |
71
+ | 0.0318 | 0.0790 | 11.6314 | 0.3628 | 0.0760 | 9.6652 | 21 |
72
+ | 0.0262 | 0.0792 | 11.4603 | 0.3728 | 0.0760 | 10.0035 | 22 |
73
+ | 0.0224 | 0.0792 | 11.4330 | 0.3824 | 0.0760 | 9.1995 | 23 |
74
+ | 0.0181 | 0.0793 | 11.3124 | 0.3982 | 0.0759 | 9.8710 | 24 |
75
+ | 0.0142 | 0.0794 | 11.3562 | 0.4057 | 0.0760 | 9.6831 | 25 |
76
+ | 0.0118 | 0.0794 | 11.0532 | 0.4207 | 0.0759 | 9.7227 | 26 |
77
+ | 0.0101 | 0.0794 | 11.2963 | 0.4282 | 0.0760 | 9.5792 | 27 |
78
+ | 0.0114 | 0.0794 | 11.3093 | 0.4431 | 0.0758 | 9.5545 | 28 |
79
+ | 0.0109 | 0.0794 | 11.4214 | 0.4419 | 0.0760 | 9.4377 | 29 |
80
+ | 0.0084 | 0.0794 | 10.9143 | 0.4474 | 0.0760 | 9.3668 | 30 |
81
+ | 0.0043 | 0.0795 | 10.9497 | 0.4525 | 0.0761 | 9.3202 | 31 |
82
+ | 0.0036 | 0.0795 | 10.7759 | 0.4667 | 0.0761 | 9.0385 | 32 |
83
+ | 0.0047 | 0.0795 | 10.7613 | 0.4788 | 0.0759 | 9.4065 | 33 |
84
+ | 0.0130 | 0.0793 | 11.1022 | 0.4748 | 0.0760 | 9.4521 | 34 |
85
+ | 0.0074 | 0.0794 | 10.9738 | 0.4730 | 0.0760 | 9.3348 | 35 |
86
+ | 0.0032 | 0.0795 | 10.6370 | 0.4750 | 0.0762 | 8.8298 | 36 |
87
+ | 0.0020 | 0.0795 | 10.7428 | 0.4835 | 0.0762 | 9.0566 | 37 |
88
+ | 0.0014 | 0.0795 | 10.6908 | 0.4937 | 0.0761 | 9.2445 | 38 |
89
+ | 0.0035 | 0.0795 | 10.6833 | 0.5276 | 0.0757 | 8.9798 | 39 |
90
+ | 0.0120 | 0.0793 | 10.4810 | 0.4963 | 0.0760 | 8.9194 | 40 |
91
+ | 0.0045 | 0.0795 | 10.2251 | 0.5014 | 0.0761 | 8.5737 | 41 |
92
+ | 0.0028 | 0.0795 | 10.3174 | 0.4968 | 0.0762 | 8.8525 | 42 |
93
+ | 0.0023 | 0.0795 | 10.4871 | 0.5027 | 0.0762 | 8.6712 | 43 |
94
+ | 0.0024 | 0.0795 | 10.3731 | 0.5055 | 0.0762 | 8.6347 | 44 |
95
+ | 0.0041 | 0.0795 | 10.2751 | 0.5242 | 0.0760 | 8.3671 | 45 |
96
+ | 0.0070 | 0.0794 | 10.2166 | 0.5169 | 0.0760 | 8.8409 | 46 |
97
+ | 0.0037 | 0.0795 | 10.0455 | 0.5174 | 0.0762 | 8.2514 | 47 |
98
+ | 0.0023 | 0.0795 | 9.9201 | 0.5167 | 0.0763 | 8.9537 | 48 |
99
+ | 0.0008 | 0.0795 | 10.0022 | 0.5166 | 0.0764 | 8.4855 | 49 |
100
+ | 0.0006 | 0.0795 | 9.9494 | 0.5233 | 0.0763 | 8.5719 | 50 |
101
+ | 0.0069 | 0.0794 | 10.2037 | 0.5434 | 0.0759 | 8.5399 | 51 |
102
+ | 0.0083 | 0.0794 | 9.9557 | 0.5173 | 0.0762 | 8.2406 | 52 |
103
+ | 0.0032 | 0.0795 | 10.0283 | 0.5240 | 0.0763 | 9.0101 | 53 |
104
+ | 0.0018 | 0.0795 | 10.0694 | 0.5247 | 0.0763 | 8.5717 | 54 |
105
+ | 0.0008 | 0.0795 | 10.1079 | 0.5217 | 0.0764 | 8.5608 | 55 |
106
+ | 0.0005 | 0.0795 | 10.0546 | 0.5286 | 0.0764 | 8.8830 | 56 |
107
+ | 0.0007 | 0.0795 | 10.2557 | 0.5328 | 0.0764 | 8.5665 | 57 |
108
+ | 0.0006 | 0.0795 | 10.2165 | 0.5412 | 0.0763 | 8.4623 | 58 |
109
+ | 0.0124 | 0.0792 | 10.2304 | 0.5284 | 0.0762 | 9.1194 | 59 |
110
+ | 0.0044 | 0.0795 | 10.3884 | 0.5223 | 0.0764 | 8.8152 | 60 |
111
+ | 0.0015 | 0.0795 | 9.8557 | 0.5227 | 0.0764 | 8.3774 | 61 |
112
+ | 0.0005 | 0.0795 | 9.8123 | 0.5233 | 0.0765 | 8.5043 | 62 |
113
+ | 0.0003 | 0.0795 | 9.7631 | 0.5282 | 0.0765 | 8.3860 | 63 |
114
+ | 0.0003 | 0.0795 | 9.7593 | 0.5320 | 0.0765 | 8.4815 | 64 |
115
+ | 0.0002 | 0.0795 | 9.7663 | 0.5357 | 0.0765 | 8.4281 | 65 |
116
+ | 0.0034 | 0.0795 | 9.8382 | 0.5771 | 0.0758 | 8.8051 | 66 |
117
+ | 0.0123 | 0.0792 | 10.2575 | 0.5261 | 0.0763 | 9.3701 | 67 |
118
+ | 0.0027 | 0.0795 | 10.3802 | 0.5272 | 0.0764 | 8.8216 | 68 |
119
+ | 0.0011 | 0.0795 | 10.1683 | 0.5291 | 0.0764 | 8.5736 | 69 |
120
+ | 0.0012 | 0.0795 | 10.1305 | 0.5336 | 0.0765 | 8.6648 | 70 |
121
+ | 0.0008 | 0.0795 | 10.2545 | 0.5315 | 0.0765 | 9.0617 | 71 |
122
+ | 0.0006 | 0.0795 | 10.4562 | 0.5369 | 0.0765 | 9.6485 | 72 |
123
+ | 0.0032 | 0.0795 | 10.2347 | 0.5569 | 0.0763 | 8.4947 | 73 |
124
+ | 0.0062 | 0.0794 | 10.1654 | 0.5471 | 0.0763 | 8.8666 | 74 |
125
+ | 0.0029 | 0.0795 | 10.1320 | 0.5376 | 0.0765 | 8.7713 | 75 |
126
+ | 0.0012 | 0.0795 | 10.2943 | 0.5406 | 0.0765 | 8.6959 | 76 |
127
+ | 0.0006 | 0.0795 | 10.1888 | 0.5371 | 0.0767 | 8.9689 | 77 |
128
+
129
+
130
+ ### Framework versions
131
+
132
+ - Transformers 4.32.0.dev0
133
+ - TensorFlow 2.12.0
134
+ - 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": "4.32.0.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": "4.32.0.dev0"
117
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26d9ead566b296b8e8fc84447524b9a5cbcbf6de4409adcce61093e403df048
3
+ size 151253960