Hugging Face's logo

bigmorning
/
whisper_4_with_init_sun__0055

Automatic Speech Recognition
Transformers
TensorFlow
whisper
generated_from_keras_callback
Inference Endpoints
Model card Files Community
bigmorning commited on
Commit
e35c7a6
•
1 Parent(s): e803fd6

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_4_with_init_sun__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_4_with_init_sun__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: 0.5275
19
+ - Train Accuracy: 0.0313
20
+ - Train Wermet: 0.1412
21
+ - Validation Loss: 1.1743
22
+ - Validation Accuracy: 0.0204
23
+ - Validation Wermet: 0.3384
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
+ | 5.3333 | 0.0111 | 1.3132 | 3.9675 | 0.0114 | 0.9339 | 0 |
51
+ | 4.7131 | 0.0116 | 0.8607 | 3.9360 | 0.0114 | 0.9503 | 1 |
52
+ | 4.6717 | 0.0117 | 0.8449 | 3.9196 | 0.0113 | 0.9768 | 2 |
53
+ | 4.6474 | 0.0117 | 0.8338 | 3.9039 | 0.0114 | 0.9557 | 3 |
54
+ | 4.6273 | 0.0118 | 0.8243 | 3.8721 | 0.0115 | 0.9414 | 4 |
55
+ | 4.6101 | 0.0118 | 0.8167 | 3.8629 | 0.0116 | 0.9156 | 5 |
56
+ | 4.5912 | 0.0119 | 0.7985 | 3.8361 | 0.0116 | 0.8988 | 6 |
57
+ | 4.5645 | 0.0120 | 0.7753 | 3.8298 | 0.0116 | 0.9045 | 7 |
58
+ | 4.5386 | 0.0121 | 0.7558 | 3.7904 | 0.0118 | 0.8426 | 8 |
59
+ | 4.5075 | 0.0122 | 0.7405 | 3.7472 | 0.0119 | 0.8103 | 9 |
60
+ | 4.4586 | 0.0124 | 0.7255 | 3.7163 | 0.0120 | 0.8189 | 10 |
61
+ | 4.3978 | 0.0126 | 0.7174 | 3.6168 | 0.0122 | 0.8163 | 11 |
62
+ | 4.3031 | 0.0128 | 0.7107 | 3.4956 | 0.0125 | 0.7847 | 12 |
63
+ | 4.1606 | 0.0133 | 0.7025 | 3.3414 | 0.0128 | 0.7897 | 13 |
64
+ | 3.9636 | 0.0138 | 0.6991 | 3.1311 | 0.0133 | 0.7495 | 14 |
65
+ | 3.7290 | 0.0145 | 0.6827 | 2.8892 | 0.0139 | 0.7292 | 15 |
66
+ | 3.4993 | 0.0152 | 0.6643 | 2.7195 | 0.0143 | 0.7129 | 16 |
67
+ | 3.2810 | 0.0159 | 0.6448 | 2.5418 | 0.0148 | 0.6803 | 17 |
68
+ | 3.0604 | 0.0167 | 0.6182 | 2.3572 | 0.0153 | 0.6538 | 18 |
69
+ | 2.8748 | 0.0174 | 0.5946 | 2.2575 | 0.0156 | 0.6337 | 19 |
70
+ | 2.6889 | 0.0181 | 0.5699 | 2.0988 | 0.0162 | 0.6016 | 20 |
71
+ | 2.5493 | 0.0187 | 0.5449 | 1.9878 | 0.0166 | 0.5834 | 21 |
72
+ | 2.3921 | 0.0194 | 0.5207 | 1.9029 | 0.0168 | 0.5597 | 22 |
73
+ | 2.2491 | 0.0201 | 0.4987 | 1.8642 | 0.0169 | 0.5409 | 23 |
74
+ | 2.1254 | 0.0207 | 0.4766 | 1.7354 | 0.0175 | 0.5231 | 24 |
75
+ | 1.9980 | 0.0213 | 0.4552 | 1.6661 | 0.0178 | 0.5049 | 25 |
76
+ | 1.9147 | 0.0217 | 0.4382 | 1.6140 | 0.0180 | 0.4921 | 26 |
77
+ | 1.8008 | 0.0223 | 0.4196 | 1.5652 | 0.0182 | 0.4742 | 27 |
78
+ | 1.7185 | 0.0228 | 0.4028 | 1.5159 | 0.0184 | 0.4632 | 28 |
79
+ | 1.6401 | 0.0232 | 0.3867 | 1.4891 | 0.0185 | 0.4548 | 29 |
80
+ | 1.5786 | 0.0235 | 0.3728 | 1.5141 | 0.0183 | 0.4548 | 30 |
81
+ | 1.4950 | 0.0241 | 0.3582 | 1.4345 | 0.0188 | 0.4340 | 31 |
82
+ | 1.4323 | 0.0244 | 0.3448 | 1.3694 | 0.0191 | 0.4226 | 32 |
83
+ | 1.3495 | 0.0250 | 0.3319 | 1.3780 | 0.0190 | 0.4172 | 33 |
84
+ | 1.3007 | 0.0253 | 0.3187 | 1.3296 | 0.0193 | 0.4109 | 34 |
85
+ | 1.2320 | 0.0257 | 0.3074 | 1.3116 | 0.0194 | 0.4029 | 35 |
86
+ | 1.1836 | 0.0261 | 0.2958 | 1.3025 | 0.0195 | 0.3992 | 36 |
87
+ | 1.1131 | 0.0266 | 0.2842 | 1.2885 | 0.0195 | 0.3894 | 37 |
88
+ | 1.0630 | 0.0269 | 0.2730 | 1.2627 | 0.0197 | 0.3850 | 38 |
89
+ | 1.0189 | 0.0272 | 0.2628 | 1.2633 | 0.0197 | 0.3822 | 39 |
90
+ | 1.0025 | 0.0273 | 0.2550 | 1.2561 | 0.0197 | 0.3760 | 40 |
91
+ | 0.9498 | 0.0277 | 0.2445 | 1.2288 | 0.0199 | 0.3710 | 41 |
92
+ | 0.9027 | 0.0281 | 0.2337 | 1.2188 | 0.0199 | 0.3684 | 42 |
93
+ | 0.8469 | 0.0286 | 0.2240 | 1.2072 | 0.0200 | 0.3637 | 43 |
94
+ | 0.8056 | 0.0289 | 0.2153 | 1.2046 | 0.0201 | 0.3599 | 44 |
95
+ | 0.7761 | 0.0291 | 0.2070 | 1.1989 | 0.0201 | 0.3579 | 45 |
96
+ | 0.7369 | 0.0295 | 0.1982 | 1.1938 | 0.0202 | 0.3528 | 46 |
97
+ | 0.7026 | 0.0298 | 0.1902 | 1.1934 | 0.0202 | 0.3508 | 47 |
98
+ | 0.6976 | 0.0298 | 0.1834 | 1.1803 | 0.0203 | 0.3469 | 48 |
99
+ | 0.6880 | 0.0298 | 0.1765 | 1.1844 | 0.0203 | 0.3470 | 49 |
100
+ | 0.6674 | 0.0300 | 0.1702 | 1.1741 | 0.0203 | 0.3446 | 50 |
101
+ | 0.6099 | 0.0305 | 0.1606 | 1.1753 | 0.0203 | 0.3440 | 51 |
102
+ | 0.5972 | 0.0306 | 0.1549 | 1.1692 | 0.0204 | 0.3401 | 52 |
103
+ | 0.5555 | 0.0310 | 0.1475 | 1.1744 | 0.0204 | 0.3382 | 53 |
104
+ | 0.5275 | 0.0313 | 0.1412 | 1.1743 | 0.0204 | 0.3384 | 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": -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 sha256:6c3821e3f27ed6ef8f8563ca87a0e69a54c6363c07187fdee40f964ca2585a9c
3
+ size 151253960