Hugging Face's logo

bigmorning
/
whisper_input_decoder_shift_r_labels_with_force__0055

Automatic Speech Recognition
Transformers
TensorFlow
whisper
generated_from_keras_callback
Inference Endpoints
Model card Files Community
bigmorning commited on
Commit
136cd98
•
1 Parent(s): 445ccdc

Upload TFWhisperForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +111 -0
  2. config.json +64 -0
  3. generation_config.json +117 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_shift_r_labels_with_force__0055
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_shift_r_labels_with_force__0055
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: 0.0222
19
+ - Train Accuracy: 0.0340
20
+ - Train Wermet: 9.9266
21
+ - Validation Loss: 0.7573
22
+ - Validation Accuracy: 0.0209
23
+ - Validation Wermet: 7.1746
24
+ - Epoch: 54
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
+ | 5.6249 | 0.0091 | 1.7162 | 4.2965 | 0.0094 | 0.9447 | 0 |
51
+ | 4.9223 | 0.0099 | 0.9041 | 4.1562 | 0.0097 | 0.9327 | 1 |
52
+ | 4.6814 | 0.0107 | 0.8376 | 3.9245 | 0.0103 | 0.8927 | 2 |
53
+ | 4.4407 | 0.0114 | 0.8311 | 3.7252 | 0.0107 | 0.8775 | 3 |
54
+ | 4.2445 | 0.0119 | 0.8228 | 3.6283 | 0.0108 | 0.8695 | 4 |
55
+ | 4.0889 | 0.0123 | 0.8067 | 3.5310 | 0.0110 | 0.8916 | 5 |
56
+ | 3.9575 | 0.0127 | 0.7908 | 3.4478 | 0.0113 | 0.8407 | 6 |
57
+ | 3.8547 | 0.0130 | 0.7781 | 3.4227 | 0.0113 | 0.8670 | 7 |
58
+ | 3.7599 | 0.0133 | 0.7654 | 3.3519 | 0.0115 | 0.8375 | 8 |
59
+ | 3.6763 | 0.0136 | 0.7543 | 3.3183 | 0.0116 | 0.8678 | 9 |
60
+ | 3.6006 | 0.0138 | 0.7421 | 3.2581 | 0.0117 | 0.8120 | 10 |
61
+ | 3.5300 | 0.0140 | 0.7296 | 3.2415 | 0.0118 | 0.8257 | 11 |
62
+ | 3.4554 | 0.0143 | 0.7179 | 3.2163 | 0.0119 | 0.8078 | 12 |
63
+ | 3.3930 | 0.0145 | 0.7057 | 3.1612 | 0.0121 | 0.7758 | 13 |
64
+ | 3.3218 | 0.0148 | 0.6946 | 3.1357 | 0.0122 | 0.7760 | 14 |
65
+ | 3.2424 | 0.0151 | 0.6806 | 3.0812 | 0.0123 | 0.7639 | 15 |
66
+ | 3.1577 | 0.0155 | 0.6633 | 3.0193 | 0.0126 | 0.7428 | 16 |
67
+ | 3.0655 | 0.0159 | 0.6454 | 2.9643 | 0.0128 | 0.7423 | 17 |
68
+ | 2.9579 | 0.0164 | 0.6271 | 2.8510 | 0.0132 | 0.7103 | 18 |
69
+ | 2.8149 | 0.0170 | 0.6022 | 2.7020 | 0.0136 | 0.6811 | 19 |
70
+ | 2.6475 | 0.0178 | 0.5775 | 2.5406 | 0.0142 | 0.6495 | 20 |
71
+ | 2.4340 | 0.0189 | 0.5451 | 2.3364 | 0.0149 | 0.6166 | 21 |
72
+ | 2.2002 | 0.0200 | 0.5065 | 2.1300 | 0.0155 | 0.5766 | 22 |
73
+ | 1.9511 | 0.0213 | 0.4658 | 1.9335 | 0.0162 | 0.5419 | 23 |
74
+ | 1.6777 | 0.0228 | 0.4184 | 1.7327 | 0.0169 | 0.5071 | 24 |
75
+ | 1.4282 | 0.0243 | 0.3754 | 1.5461 | 0.0176 | 0.4669 | 25 |
76
+ | 1.2219 | 0.0255 | 0.3365 | 1.4027 | 0.0181 | 0.4326 | 26 |
77
+ | 1.0535 | 0.0265 | 0.3016 | 1.2979 | 0.0185 | 0.4134 | 27 |
78
+ | 0.9205 | 0.0274 | 0.2731 | 1.1891 | 0.0189 | 0.3843 | 28 |
79
+ | 0.8079 | 0.0281 | 0.2453 | 1.1135 | 0.0192 | 0.3659 | 29 |
80
+ | 0.7140 | 0.0288 | 0.2218 | 1.0532 | 0.0195 | 0.3495 | 30 |
81
+ | 0.6318 | 0.0293 | 0.1975 | 0.9976 | 0.0197 | 0.3351 | 31 |
82
+ | 0.5623 | 0.0298 | 0.1770 | 0.9571 | 0.0199 | 0.3256 | 32 |
83
+ | 0.4990 | 0.0303 | 0.1582 | 0.9184 | 0.0200 | 0.3147 | 33 |
84
+ | 0.4444 | 0.0307 | 0.1424 | 0.8865 | 0.0202 | 0.3062 | 34 |
85
+ | 0.3949 | 0.0311 | 0.1260 | 0.8532 | 0.0203 | 0.2968 | 35 |
86
+ | 0.3505 | 0.0314 | 0.1118 | 0.8333 | 0.0204 | 0.2898 | 36 |
87
+ | 0.3104 | 0.0317 | 0.0988 | 0.8245 | 0.0204 | 0.2881 | 37 |
88
+ | 0.2743 | 0.0321 | 0.0886 | 0.8014 | 0.0205 | 0.2825 | 38 |
89
+ | 0.2428 | 0.0323 | 0.0842 | 0.7944 | 0.0206 | 0.2794 | 39 |
90
+ | 0.2120 | 0.0326 | 0.0880 | 0.7742 | 0.0206 | 0.2762 | 40 |
91
+ | 0.1863 | 0.0328 | 0.1289 | 0.7744 | 0.0206 | 0.2863 | 41 |
92
+ | 0.1621 | 0.0330 | 0.1792 | 0.7683 | 0.0207 | 0.2873 | 42 |
93
+ | 0.1390 | 0.0332 | 0.1918 | 0.7664 | 0.0207 | 0.4006 | 43 |
94
+ | 0.1194 | 0.0334 | 0.3137 | 0.7596 | 0.0207 | 0.5479 | 44 |
95
+ | 0.1022 | 0.0335 | 0.5546 | 0.7607 | 0.0208 | 0.8384 | 45 |
96
+ | 0.0880 | 0.0337 | 0.9275 | 0.7595 | 0.0208 | 0.8106 | 46 |
97
+ | 0.0740 | 0.0338 | 1.7784 | 0.7555 | 0.0208 | 0.9209 | 47 |
98
+ | 0.0622 | 0.0338 | 2.6518 | 0.7572 | 0.0208 | 2.2106 | 48 |
99
+ | 0.0528 | 0.0339 | 2.2627 | 0.7565 | 0.0208 | 1.4870 | 49 |
100
+ | 0.0453 | 0.0339 | 4.0945 | 0.7590 | 0.0208 | 3.1276 | 50 |
101
+ | 0.0407 | 0.0339 | 6.6959 | 0.7542 | 0.0208 | 6.1620 | 51 |
102
+ | 0.0327 | 0.0340 | 7.6116 | 0.7558 | 0.0208 | 8.6756 | 52 |
103
+ | 0.0264 | 0.0340 | 11.0921 | 0.7526 | 0.0209 | 7.4669 | 53 |
104
+ | 0.0222 | 0.0340 | 9.9266 | 0.7573 | 0.0209 | 7.1746 | 54 |
105
+
106
+
107
+ ### Framework versions
108
+
109
+ - Transformers 4.34.0.dev0
110
+ - TensorFlow 2.13.0
111
+ - 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": "4.34.0.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:a11862f58bb9a8e4bd2736933f6d87816a532a8e10ef3976a3094735b0b29472
3
+ size 151253960