bigmorning commited on
Commit
c0fd226
1 Parent(s): 662f85c

Upload TFWhisperForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +81 -0
  2. config.json +51 -0
  3. generation_config.json +117 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_noforce__0025
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_noforce__0025
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: 1.5286
19
+ - Train Accuracy: 0.0253
20
+ - Train Wermet: 0.4182
21
+ - Validation Loss: 1.5139
22
+ - Validation Accuracy: 0.0194
23
+ - Validation Wermet: 0.4919
24
+ - Epoch: 24
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
+ | 5.2961 | 0.0113 | 1.9043 | 3.9402 | 0.0116 | 0.9526 | 0 |
51
+ | 4.6207 | 0.0121 | 0.8740 | 3.7957 | 0.0120 | 0.9397 | 1 |
52
+ | 4.4142 | 0.0128 | 0.8473 | 3.6045 | 0.0124 | 0.8988 | 2 |
53
+ | 4.1915 | 0.0135 | 0.8361 | 3.4445 | 0.0128 | 0.9019 | 3 |
54
+ | 4.0072 | 0.0140 | 0.8260 | 3.3268 | 0.0131 | 0.8816 | 4 |
55
+ | 3.8559 | 0.0145 | 0.8084 | 3.2440 | 0.0133 | 0.8592 | 5 |
56
+ | 3.7359 | 0.0149 | 0.7986 | 3.1751 | 0.0135 | 0.8598 | 6 |
57
+ | 3.6368 | 0.0152 | 0.7891 | 3.1298 | 0.0136 | 0.8398 | 7 |
58
+ | 3.5465 | 0.0154 | 0.7775 | 3.0736 | 0.0138 | 0.8606 | 8 |
59
+ | 3.4710 | 0.0157 | 0.7681 | 3.0318 | 0.0138 | 0.8455 | 9 |
60
+ | 3.3988 | 0.0159 | 0.7603 | 3.0159 | 0.0139 | 0.8770 | 10 |
61
+ | 3.3279 | 0.0162 | 0.7504 | 2.9672 | 0.0141 | 0.8241 | 11 |
62
+ | 3.2611 | 0.0164 | 0.7397 | 2.9541 | 0.0141 | 0.8676 | 12 |
63
+ | 3.1996 | 0.0167 | 0.7284 | 2.8913 | 0.0144 | 0.7990 | 13 |
64
+ | 3.1311 | 0.0169 | 0.7162 | 2.8671 | 0.0145 | 0.7934 | 14 |
65
+ | 3.0590 | 0.0172 | 0.7044 | 2.8241 | 0.0146 | 0.7907 | 15 |
66
+ | 2.9692 | 0.0177 | 0.6843 | 2.7517 | 0.0149 | 0.7645 | 16 |
67
+ | 2.8783 | 0.0181 | 0.6630 | 2.6682 | 0.0152 | 0.7263 | 17 |
68
+ | 2.7622 | 0.0187 | 0.6417 | 2.5586 | 0.0156 | 0.7220 | 18 |
69
+ | 2.6164 | 0.0194 | 0.6138 | 2.4121 | 0.0161 | 0.6909 | 19 |
70
+ | 2.4405 | 0.0203 | 0.5838 | 2.2417 | 0.0167 | 0.6527 | 20 |
71
+ | 2.2404 | 0.0213 | 0.5486 | 2.1401 | 0.0170 | 0.6662 | 21 |
72
+ | 2.0196 | 0.0225 | 0.5086 | 1.8907 | 0.0180 | 0.5774 | 22 |
73
+ | 1.7917 | 0.0237 | 0.4665 | 1.7073 | 0.0186 | 0.5446 | 23 |
74
+ | 1.5286 | 0.0253 | 0.4182 | 1.5139 | 0.0194 | 0.4919 | 24 |
75
+
76
+
77
+ ### Framework versions
78
+
79
+ - Transformers 4.33.0.dev0
80
+ - TensorFlow 2.13.0
81
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "init_std": 0.02,
29
+ "is_encoder_decoder": true,
30
+ "mask_feature_length": 10,
31
+ "mask_feature_min_masks": 0,
32
+ "mask_feature_prob": 0.0,
33
+ "mask_time_length": 10,
34
+ "mask_time_min_masks": 2,
35
+ "mask_time_prob": 0.05,
36
+ "max_length": 448,
37
+ "max_source_positions": 1500,
38
+ "max_target_positions": 448,
39
+ "median_filter_width": 7,
40
+ "model_type": "whisper",
41
+ "num_hidden_layers": 4,
42
+ "num_mel_bins": 80,
43
+ "pad_token_id": -100,
44
+ "scale_embedding": false,
45
+ "suppress_tokens": [],
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.33.0.dev0",
48
+ "use_cache": true,
49
+ "use_weighted_layer_sum": false,
50
+ "vocab_size": 51865
51
+ }
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:bd6a0be84b39106929d3a169e926a5fef8329ce4c7b6296b2d8f77dbf95db726
3
+ size 151253960