bigmorning commited on
Commit
fcb42de
1 Parent(s): 604d6bb

Upload TFWhisperForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +24 -24
  2. config.json +8 -1
  3. generation_config.json +219 -0
  4. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,12 +14,12 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.2807
18
- - Train Accuracy: 0.0326
19
- - Train Wermet: 5.9455
20
- - Validation Loss: 0.5636
21
- - Validation Accuracy: 0.0313
22
- - Validation Wermet: 5.3382
23
  - Epoch: 14
24
 
25
  ## Model description
@@ -46,26 +46,26 @@ The following hyperparameters were used during training:
46
 
47
  | Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
48
  |:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
49
- | 5.0860 | 0.0116 | 45.4352 | 4.4455 | 0.0124 | 36.1611 | 0 |
50
- | 4.3098 | 0.0131 | 29.4890 | 4.0321 | 0.0144 | 24.9514 | 1 |
51
- | 3.6711 | 0.0160 | 25.7380 | 2.7995 | 0.0205 | 32.2126 | 2 |
52
- | 2.2582 | 0.0224 | 31.5946 | 1.6772 | 0.0257 | 23.9282 | 3 |
53
- | 1.4268 | 0.0262 | 23.3380 | 1.2097 | 0.0279 | 18.7331 | 4 |
54
- | 1.0613 | 0.0279 | 13.6764 | 0.9972 | 0.0289 | 10.7707 | 5 |
55
- | 0.8545 | 0.0290 | 9.2746 | 0.8605 | 0.0296 | 6.5566 | 6 |
56
- | 0.7144 | 0.0297 | 7.4723 | 0.7768 | 0.0300 | 5.4825 | 7 |
57
- | 0.6116 | 0.0303 | 6.9092 | 0.7125 | 0.0304 | 6.5220 | 8 |
58
- | 0.5307 | 0.0308 | 6.4113 | 0.6640 | 0.0306 | 5.7589 | 9 |
59
- | 0.4647 | 0.0312 | 5.5865 | 0.6338 | 0.0309 | 4.8846 | 10 |
60
- | 0.4085 | 0.0316 | 5.9874 | 0.6035 | 0.0310 | 3.8731 | 11 |
61
- | 0.3602 | 0.0320 | 5.5558 | 0.5838 | 0.0311 | 6.3441 | 12 |
62
- | 0.3184 | 0.0323 | 6.2887 | 0.5690 | 0.0312 | 3.9274 | 13 |
63
- | 0.2807 | 0.0326 | 5.9455 | 0.5636 | 0.0313 | 5.3382 | 14 |
64
 
65
 
66
  ### Framework versions
67
 
68
- - Transformers 4.25.0.dev0
69
- - TensorFlow 2.9.2
70
- - Datasets 2.6.1
71
  - Tokenizers 0.13.2
 
14
 
15
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.2198
18
+ - Train Accuracy: 0.0320
19
+ - Train Wermet: 3.8215
20
+ - Validation Loss: 0.4835
21
+ - Validation Accuracy: 0.0311
22
+ - Validation Wermet: 4.4217
23
  - Epoch: 14
24
 
25
  ## Model description
 
46
 
47
  | Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch |
48
  |:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:|
49
+ | 5.0729 | 0.0113 | 42.1824 | 4.4421 | 0.0120 | 27.3059 | 0 |
50
+ | 4.3249 | 0.0126 | 23.9224 | 4.0443 | 0.0141 | 18.2054 | 1 |
51
+ | 3.8845 | 0.0144 | 12.7780 | 3.4577 | 0.0169 | 10.3356 | 2 |
52
+ | 2.7411 | 0.0198 | 15.0018 | 1.8774 | 0.0244 | 14.5666 | 3 |
53
+ | 1.5621 | 0.0250 | 9.7248 | 1.2443 | 0.0273 | 5.4731 | 4 |
54
+ | 1.0745 | 0.0272 | 7.1512 | 0.9802 | 0.0285 | 4.4745 | 5 |
55
+ | 0.8261 | 0.0284 | 6.2358 | 0.8209 | 0.0293 | 5.6600 | 6 |
56
+ | 0.6673 | 0.0292 | 5.8338 | 0.7182 | 0.0298 | 4.0874 | 7 |
57
+ | 0.5548 | 0.0298 | 5.0555 | 0.6489 | 0.0301 | 4.4537 | 8 |
58
+ | 0.4694 | 0.0303 | 4.3895 | 0.6038 | 0.0304 | 2.8294 | 9 |
59
+ | 0.4011 | 0.0307 | 4.4178 | 0.5673 | 0.0306 | 3.5806 | 10 |
60
+ | 0.3446 | 0.0311 | 4.1189 | 0.5329 | 0.0308 | 4.7372 | 11 |
61
+ | 0.2968 | 0.0314 | 3.9189 | 0.5138 | 0.0309 | 2.2499 | 12 |
62
+ | 0.2553 | 0.0317 | 3.7758 | 0.4990 | 0.0310 | 3.3427 | 13 |
63
+ | 0.2198 | 0.0320 | 3.8215 | 0.4835 | 0.0311 | 4.4217 | 14 |
64
 
65
 
66
  ### Framework versions
67
 
68
+ - Transformers 4.27.0.dev0
69
+ - TensorFlow 2.11.0
70
+ - Datasets 2.10.0
71
  - Tokenizers 0.13.2
config.json CHANGED
@@ -2,6 +2,7 @@
2
  "_name_or_path": "openai/whisper-tiny",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
 
5
  "architectures": [
6
  "WhisperForConditionalGeneration"
7
  ],
@@ -26,6 +27,12 @@
26
  "forced_decoder_ids": null,
27
  "init_std": 0.02,
28
  "is_encoder_decoder": true,
 
 
 
 
 
 
29
  "max_length": 448,
30
  "max_source_positions": 1500,
31
  "max_target_positions": 448,
@@ -36,7 +43,7 @@
36
  "scale_embedding": false,
37
  "suppress_tokens": [],
38
  "torch_dtype": "float32",
39
- "transformers_version": "4.25.0.dev0",
40
  "use_cache": true,
41
  "vocab_size": 51865
42
  }
 
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
  ],
 
27
  "forced_decoder_ids": null,
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,
 
43
  "scale_embedding": false,
44
  "suppress_tokens": [],
45
  "torch_dtype": "float32",
46
+ "transformers_version": "4.27.0.dev0",
47
  "use_cache": true,
48
  "vocab_size": 51865
49
  }
generation_config.json ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "begin_suppress_tokens": [
3
+ 220,
4
+ 50257
5
+ ],
6
+ "bos_token_id": 50257,
7
+ "decoder_start_token_id": 50258,
8
+ "eos_token_id": 50257,
9
+ "forced_decoder_ids": [
10
+ [
11
+ 1,
12
+ null
13
+ ],
14
+ [
15
+ 2,
16
+ 50359
17
+ ]
18
+ ],
19
+ "is_multilingual": true,
20
+ "lang_to_id": {
21
+ "<|af|>": 50327,
22
+ "<|am|>": 50334,
23
+ "<|ar|>": 50272,
24
+ "<|as|>": 50350,
25
+ "<|az|>": 50304,
26
+ "<|ba|>": 50355,
27
+ "<|be|>": 50330,
28
+ "<|bg|>": 50292,
29
+ "<|bn|>": 50302,
30
+ "<|bo|>": 50347,
31
+ "<|br|>": 50309,
32
+ "<|bs|>": 50315,
33
+ "<|ca|>": 50270,
34
+ "<|cs|>": 50283,
35
+ "<|cy|>": 50297,
36
+ "<|da|>": 50285,
37
+ "<|de|>": 50261,
38
+ "<|el|>": 50281,
39
+ "<|en|>": 50259,
40
+ "<|es|>": 50262,
41
+ "<|et|>": 50307,
42
+ "<|eu|>": 50310,
43
+ "<|fa|>": 50300,
44
+ "<|fi|>": 50277,
45
+ "<|fo|>": 50338,
46
+ "<|fr|>": 50265,
47
+ "<|gl|>": 50319,
48
+ "<|gu|>": 50333,
49
+ "<|haw|>": 50352,
50
+ "<|ha|>": 50354,
51
+ "<|he|>": 50279,
52
+ "<|hi|>": 50276,
53
+ "<|hr|>": 50291,
54
+ "<|ht|>": 50339,
55
+ "<|hu|>": 50286,
56
+ "<|hy|>": 50312,
57
+ "<|id|>": 50275,
58
+ "<|is|>": 50311,
59
+ "<|it|>": 50274,
60
+ "<|ja|>": 50266,
61
+ "<|jw|>": 50356,
62
+ "<|ka|>": 50329,
63
+ "<|kk|>": 50316,
64
+ "<|km|>": 50323,
65
+ "<|kn|>": 50306,
66
+ "<|ko|>": 50264,
67
+ "<|la|>": 50294,
68
+ "<|lb|>": 50345,
69
+ "<|ln|>": 50353,
70
+ "<|lo|>": 50336,
71
+ "<|lt|>": 50293,
72
+ "<|lv|>": 50301,
73
+ "<|mg|>": 50349,
74
+ "<|mi|>": 50295,
75
+ "<|mk|>": 50308,
76
+ "<|ml|>": 50296,
77
+ "<|mn|>": 50314,
78
+ "<|mr|>": 50320,
79
+ "<|ms|>": 50282,
80
+ "<|mt|>": 50343,
81
+ "<|my|>": 50346,
82
+ "<|ne|>": 50313,
83
+ "<|nl|>": 50271,
84
+ "<|nn|>": 50342,
85
+ "<|no|>": 50288,
86
+ "<|oc|>": 50328,
87
+ "<|pa|>": 50321,
88
+ "<|pl|>": 50269,
89
+ "<|ps|>": 50340,
90
+ "<|pt|>": 50267,
91
+ "<|ro|>": 50284,
92
+ "<|ru|>": 50263,
93
+ "<|sa|>": 50344,
94
+ "<|sd|>": 50332,
95
+ "<|si|>": 50322,
96
+ "<|sk|>": 50298,
97
+ "<|sl|>": 50305,
98
+ "<|sn|>": 50324,
99
+ "<|so|>": 50326,
100
+ "<|sq|>": 50317,
101
+ "<|sr|>": 50303,
102
+ "<|su|>": 50357,
103
+ "<|sv|>": 50273,
104
+ "<|sw|>": 50318,
105
+ "<|ta|>": 50287,
106
+ "<|te|>": 50299,
107
+ "<|tg|>": 50331,
108
+ "<|th|>": 50289,
109
+ "<|tk|>": 50341,
110
+ "<|tl|>": 50348,
111
+ "<|tr|>": 50268,
112
+ "<|tt|>": 50351,
113
+ "<|uk|>": 50280,
114
+ "<|ur|>": 50290,
115
+ "<|uz|>": 50337,
116
+ "<|vi|>": 50278,
117
+ "<|yi|>": 50335,
118
+ "<|yo|>": 50325,
119
+ "<|zh|>": 50260
120
+ },
121
+ "max_initial_timestamp_index": 1,
122
+ "max_length": 448,
123
+ "no_timestamps_token_id": 50363,
124
+ "pad_token_id": 50256,
125
+ "return_timestamps": false,
126
+ "suppress_tokens": [
127
+ 1,
128
+ 2,
129
+ 7,
130
+ 8,
131
+ 9,
132
+ 10,
133
+ 14,
134
+ 25,
135
+ 26,
136
+ 27,
137
+ 28,
138
+ 29,
139
+ 31,
140
+ 58,
141
+ 59,
142
+ 60,
143
+ 61,
144
+ 62,
145
+ 63,
146
+ 90,
147
+ 91,
148
+ 92,
149
+ 93,
150
+ 359,
151
+ 503,
152
+ 522,
153
+ 542,
154
+ 873,
155
+ 893,
156
+ 902,
157
+ 918,
158
+ 922,
159
+ 931,
160
+ 1350,
161
+ 1853,
162
+ 1982,
163
+ 2460,
164
+ 2627,
165
+ 3246,
166
+ 3253,
167
+ 3268,
168
+ 3536,
169
+ 3846,
170
+ 3961,
171
+ 4183,
172
+ 4667,
173
+ 6585,
174
+ 6647,
175
+ 7273,
176
+ 9061,
177
+ 9383,
178
+ 10428,
179
+ 10929,
180
+ 11938,
181
+ 12033,
182
+ 12331,
183
+ 12562,
184
+ 13793,
185
+ 14157,
186
+ 14635,
187
+ 15265,
188
+ 15618,
189
+ 16553,
190
+ 16604,
191
+ 18362,
192
+ 18956,
193
+ 20075,
194
+ 21675,
195
+ 22520,
196
+ 26130,
197
+ 26161,
198
+ 26435,
199
+ 28279,
200
+ 29464,
201
+ 31650,
202
+ 32302,
203
+ 32470,
204
+ 36865,
205
+ 42863,
206
+ 47425,
207
+ 49870,
208
+ 50254,
209
+ 50258,
210
+ 50360,
211
+ 50361,
212
+ 50362
213
+ ],
214
+ "task_to_id": {
215
+ "transcribe": 50359,
216
+ "translate": 50358
217
+ },
218
+ "transformers_version": "4.27.0.dev0"
219
+ }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7fd45145c12f7e6921c4eabea6fccd0039cad88857d78c716f94dfca8f95ee5
3
  size 151253984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdfc94efa028b26b1f83d1ff5d33aff6b3b4b6206cc12c694f81e827369b630f
3
  size 151253984