Hugging Face's logo

bigmorning
/
whisper_syl_cv12_pad_lob100__0050

Automatic Speech Recognition
Transformers
TensorFlow
whisper
generated_from_keras_callback
Inference Endpoints
Model card Files Community
bigmorning commited on
Commit
09cd2a7
•
1 Parent(s): ce50bd5

Upload TFWhisperForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +106 -0
  2. config.json +64 -0
  3. generation_config.json +117 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_syl_cv12_pad_lob100__0050
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_syl_cv12_pad_lob100__0050
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: 0.0071
19
+ - Train Accuracy: 0.0362
20
+ - Train Wermet: 0.3045
21
+ - Validation Loss: 0.6047
22
+ - Validation Accuracy: 0.0237
23
+ - Validation Wermet: 0.7476
24
+ - Epoch: 49
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': 2e-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
+ | 5.0233 | 0.0115 | 1.6383 | 3.8616 | 0.0117 | 0.9516 | 0 |
51
+ | 4.4412 | 0.0127 | 0.8560 | 3.5410 | 0.0125 | 0.8971 | 1 |
52
+ | 4.0719 | 0.0138 | 0.8366 | 3.2944 | 0.0132 | 0.8706 | 2 |
53
+ | 3.8091 | 0.0146 | 0.8133 | 3.1691 | 0.0134 | 0.8487 | 3 |
54
+ | 3.6239 | 0.0152 | 0.7866 | 3.0647 | 0.0136 | 0.8282 | 4 |
55
+ | 3.4749 | 0.0156 | 0.7589 | 2.9835 | 0.0139 | 0.8049 | 5 |
56
+ | 3.3444 | 0.0161 | 0.7359 | 2.9351 | 0.0140 | 0.7979 | 6 |
57
+ | 3.2215 | 0.0165 | 0.7138 | 2.8468 | 0.0145 | 0.7589 | 7 |
58
+ | 3.0754 | 0.0172 | 0.6873 | 2.7530 | 0.0148 | 0.7413 | 8 |
59
+ | 2.8713 | 0.0181 | 0.6484 | 2.5226 | 0.0157 | 0.7017 | 9 |
60
+ | 2.5469 | 0.0197 | 0.5934 | 2.1931 | 0.0168 | 0.6285 | 10 |
61
+ | 2.0233 | 0.0225 | 0.4997 | 1.6411 | 0.0189 | 0.5215 | 11 |
62
+ | 1.3808 | 0.0264 | 0.3852 | 1.2401 | 0.0205 | 0.4238 | 12 |
63
+ | 0.9722 | 0.0290 | 0.3123 | 1.0195 | 0.0215 | 0.3682 | 13 |
64
+ | 0.7388 | 0.0305 | 0.2828 | 0.8773 | 0.0221 | 0.3322 | 14 |
65
+ | 0.5787 | 0.0317 | 0.2751 | 0.7970 | 0.0225 | 0.3083 | 15 |
66
+ | 0.4642 | 0.0325 | 0.2878 | 0.7315 | 0.0227 | 0.2964 | 16 |
67
+ | 0.3752 | 0.0332 | 0.4217 | 0.6897 | 0.0229 | 0.3297 | 17 |
68
+ | 0.3042 | 0.0338 | 0.7294 | 0.6572 | 0.0231 | 0.4453 | 18 |
69
+ | 0.2444 | 0.0343 | 1.1298 | 0.6369 | 0.0232 | 0.6637 | 19 |
70
+ | 0.1949 | 0.0348 | 1.6370 | 0.6180 | 0.0233 | 1.6119 | 20 |
71
+ | 0.1544 | 0.0352 | 1.6151 | 0.6149 | 0.0233 | 1.6843 | 21 |
72
+ | 0.1212 | 0.0355 | 1.3832 | 0.6066 | 0.0233 | 0.8721 | 22 |
73
+ | 0.0931 | 0.0357 | 1.2799 | 0.6034 | 0.0234 | 0.5109 | 23 |
74
+ | 0.0725 | 0.0359 | 1.0940 | 0.6102 | 0.0234 | 1.0111 | 24 |
75
+ | 0.0551 | 0.0361 | 1.2865 | 0.6000 | 0.0234 | 1.1393 | 25 |
76
+ | 0.0411 | 0.0361 | 1.8511 | 0.6037 | 0.0235 | 2.0574 | 26 |
77
+ | 0.0311 | 0.0362 | 1.7179 | 0.6018 | 0.0235 | 1.4847 | 27 |
78
+ | 0.0253 | 0.0362 | 0.9801 | 0.6010 | 0.0235 | 0.4457 | 28 |
79
+ | 0.0231 | 0.0362 | 0.9376 | 0.6046 | 0.0235 | 0.9247 | 29 |
80
+ | 0.0196 | 0.0362 | 0.6466 | 0.6078 | 0.0235 | 0.5271 | 30 |
81
+ | 0.0177 | 0.0362 | 0.4041 | 0.6155 | 0.0235 | 0.4352 | 31 |
82
+ | 0.0139 | 0.0362 | 0.4202 | 0.6037 | 0.0236 | 0.5585 | 32 |
83
+ | 0.0137 | 0.0362 | 0.8151 | 0.6015 | 0.0236 | 1.8476 | 33 |
84
+ | 0.0122 | 0.0362 | 3.4515 | 0.6043 | 0.0236 | 3.8210 | 34 |
85
+ | 0.0098 | 0.0362 | 1.1787 | 0.5985 | 0.0236 | 0.8094 | 35 |
86
+ | 0.0071 | 0.0362 | 0.9920 | 0.5992 | 0.0236 | 0.8755 | 36 |
87
+ | 0.0055 | 0.0362 | 2.4665 | 0.6047 | 0.0236 | 2.0127 | 37 |
88
+ | 0.0124 | 0.0362 | 4.2468 | 0.6089 | 0.0236 | 2.8886 | 38 |
89
+ | 0.0109 | 0.0362 | 2.0177 | 0.6097 | 0.0236 | 0.3417 | 39 |
90
+ | 0.0073 | 0.0362 | 0.9927 | 0.6057 | 0.0237 | 2.5519 | 40 |
91
+ | 0.0080 | 0.0362 | 1.7341 | 0.6099 | 0.0236 | 1.3119 | 41 |
92
+ | 0.0063 | 0.0362 | 2.4288 | 0.6058 | 0.0237 | 1.3465 | 42 |
93
+ | 0.0038 | 0.0362 | 1.4535 | 0.6022 | 0.0237 | 1.6804 | 43 |
94
+ | 0.0028 | 0.0362 | 2.2629 | 0.6001 | 0.0238 | 3.4388 | 44 |
95
+ | 0.0021 | 0.0362 | 3.5877 | 0.6018 | 0.0238 | 2.6165 | 45 |
96
+ | 0.0017 | 0.0362 | 3.0080 | 0.6043 | 0.0238 | 2.6827 | 46 |
97
+ | 0.0061 | 0.0362 | 2.5182 | 0.6545 | 0.0235 | 0.2316 | 47 |
98
+ | 0.0126 | 0.0362 | 0.2097 | 0.6206 | 0.0236 | 0.6194 | 48 |
99
+ | 0.0071 | 0.0362 | 0.3045 | 0.6047 | 0.0237 | 0.7476 | 49 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.33.0.dev0
105
+ - TensorFlow 2.13.0
106
+ - 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 sha256:92746757375b5806bfa6293d66818d79ef9b127f23e1548e303db4ee3fe7cb70
3
+ size 151253960