ZHProject23 commited on
Commit
1514bfa
·
1 Parent(s): dabf8e5

Model save

Browse files
Files changed (3) hide show
  1. README.md +134 -0
  2. generation_config.json +263 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: openai/whisper-small
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: whisper-small-vn
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # whisper-small-vn
17
+
18
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.2044
21
+ - Wer: 11.5097
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 8
47
+ - training_steps: 148
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 4.5043 | 0.01 | 2 | 4.4639 | 33.6957 |
54
+ | 4.0539 | 0.03 | 4 | 3.7975 | 35.9783 |
55
+ | 3.3205 | 0.04 | 6 | 3.0084 | 37.2101 |
56
+ | 2.7077 | 0.05 | 8 | 2.5555 | 37.9710 |
57
+ | 2.2203 | 0.07 | 10 | 2.2051 | 63.5870 |
58
+ | 2.1151 | 0.08 | 12 | 1.9006 | 132.9227 |
59
+ | 2.0148 | 0.09 | 14 | 1.6122 | 134.7222 |
60
+ | 1.2862 | 0.11 | 16 | 1.3244 | 144.0821 |
61
+ | 1.207 | 0.12 | 18 | 1.0984 | 110.8575 |
62
+ | 1.146 | 0.14 | 20 | 1.0196 | 105.2053 |
63
+ | 1.0035 | 0.15 | 22 | 0.9752 | 99.8792 |
64
+ | 0.8611 | 0.16 | 24 | 0.9322 | 80.3986 |
65
+ | 0.8995 | 0.18 | 26 | 0.8938 | 69.0700 |
66
+ | 0.9165 | 0.19 | 28 | 0.8634 | 55.9058 |
67
+ | 0.9399 | 0.2 | 30 | 0.8389 | 44.5894 |
68
+ | 0.7586 | 0.22 | 32 | 0.8171 | 38.1884 |
69
+ | 0.7416 | 0.23 | 34 | 0.7963 | 34.4444 |
70
+ | 0.8141 | 0.24 | 36 | 0.7765 | 31.9082 |
71
+ | 0.8389 | 0.26 | 38 | 0.7578 | 34.1546 |
72
+ | 0.753 | 0.27 | 40 | 0.7393 | 42.6449 |
73
+ | 0.756 | 0.28 | 42 | 0.7228 | 54.4203 |
74
+ | 0.7347 | 0.3 | 44 | 0.7077 | 66.2681 |
75
+ | 0.6526 | 0.31 | 46 | 0.6939 | 49.2874 |
76
+ | 0.5208 | 0.32 | 48 | 0.6803 | 31.5821 |
77
+ | 0.7804 | 0.34 | 50 | 0.6657 | 35.3261 |
78
+ | 0.6831 | 0.35 | 52 | 0.6524 | 39.2995 |
79
+ | 0.5237 | 0.36 | 54 | 0.6409 | 42.6087 |
80
+ | 0.6799 | 0.38 | 56 | 0.6305 | 40.0966 |
81
+ | 0.681 | 0.39 | 58 | 0.6195 | 44.2754 |
82
+ | 0.5804 | 0.41 | 60 | 0.6062 | 42.2101 |
83
+ | 0.5869 | 0.42 | 62 | 0.5930 | 44.9517 |
84
+ | 0.7131 | 0.43 | 64 | 0.5805 | 41.4734 |
85
+ | 0.7012 | 0.45 | 66 | 0.5689 | 42.1498 |
86
+ | 0.6513 | 0.46 | 68 | 0.5576 | 41.9203 |
87
+ | 0.4762 | 0.47 | 70 | 0.5460 | 43.0193 |
88
+ | 0.503 | 0.49 | 72 | 0.5333 | 46.2198 |
89
+ | 0.5342 | 0.5 | 74 | 0.5200 | 48.1522 |
90
+ | 0.4769 | 0.51 | 76 | 0.5055 | 45.3382 |
91
+ | 0.3922 | 0.53 | 78 | 0.4910 | 46.6667 |
92
+ | 0.4501 | 0.54 | 80 | 0.4752 | 49.5169 |
93
+ | 0.4469 | 0.55 | 82 | 0.4574 | 50.8092 |
94
+ | 0.5398 | 0.57 | 84 | 0.4356 | 50.5797 |
95
+ | 0.3611 | 0.58 | 86 | 0.4053 | 48.2246 |
96
+ | 0.4015 | 0.59 | 88 | 0.3565 | 44.9275 |
97
+ | 0.3192 | 0.61 | 90 | 0.2724 | 46.4493 |
98
+ | 0.2466 | 0.62 | 92 | 0.2516 | 47.1256 |
99
+ | 0.2147 | 0.64 | 94 | 0.2574 | 35.0483 |
100
+ | 0.1898 | 0.65 | 96 | 0.2431 | 23.8527 |
101
+ | 0.2059 | 0.66 | 98 | 0.2314 | 17.1981 |
102
+ | 0.2634 | 0.68 | 100 | 0.2258 | 15.1208 |
103
+ | 0.1498 | 0.69 | 102 | 0.2223 | 14.3599 |
104
+ | 0.2672 | 0.7 | 104 | 0.2202 | 13.9130 |
105
+ | 0.0989 | 0.72 | 106 | 0.2192 | 13.5024 |
106
+ | 0.2685 | 0.73 | 108 | 0.2181 | 13.1280 |
107
+ | 0.1886 | 0.74 | 110 | 0.2168 | 12.8744 |
108
+ | 0.3012 | 0.76 | 112 | 0.2155 | 12.7174 |
109
+ | 0.2134 | 0.77 | 114 | 0.2143 | 12.3792 |
110
+ | 0.3099 | 0.78 | 116 | 0.2133 | 12.3188 |
111
+ | 0.336 | 0.8 | 118 | 0.2124 | 12.2826 |
112
+ | 0.1386 | 0.81 | 120 | 0.2112 | 12.0652 |
113
+ | 0.1756 | 0.82 | 122 | 0.2100 | 11.9807 |
114
+ | 0.2789 | 0.84 | 124 | 0.2092 | 11.8237 |
115
+ | 0.1284 | 0.85 | 126 | 0.2085 | 11.7512 |
116
+ | 0.2586 | 0.86 | 128 | 0.2078 | 11.6304 |
117
+ | 0.31 | 0.88 | 130 | 0.2072 | 11.5942 |
118
+ | 0.1971 | 0.89 | 132 | 0.2067 | 11.5700 |
119
+ | 0.2664 | 0.91 | 134 | 0.2062 | 11.5459 |
120
+ | 0.2684 | 0.92 | 136 | 0.2058 | 11.5459 |
121
+ | 0.4082 | 0.93 | 138 | 0.2053 | 11.4976 |
122
+ | 0.2593 | 0.95 | 140 | 0.2050 | 11.4855 |
123
+ | 0.143 | 0.96 | 142 | 0.2048 | 11.4976 |
124
+ | 0.2015 | 0.97 | 144 | 0.2046 | 11.5097 |
125
+ | 0.1958 | 0.99 | 146 | 0.2045 | 11.5217 |
126
+ | 0.3197 | 1.0 | 148 | 0.2044 | 11.5097 |
127
+
128
+
129
+ ### Framework versions
130
+
131
+ - Transformers 4.37.0.dev0
132
+ - Pytorch 2.0.0+cu117
133
+ - Datasets 2.15.0
134
+ - Tokenizers 0.15.0
generation_config.json ADDED
@@ -0,0 +1,263 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
42
+ ]
43
+ ],
44
+ "begin_suppress_tokens": [
45
+ 220,
46
+ 50257
47
+ ],
48
+ "bos_token_id": 50257,
49
+ "decoder_start_token_id": 50258,
50
+ "eos_token_id": 50257,
51
+ "forced_decoder_ids": [
52
+ [
53
+ 1,
54
+ null
55
+ ],
56
+ [
57
+ 2,
58
+ 50359
59
+ ]
60
+ ],
61
+ "is_multilingual": true,
62
+ "lang_to_id": {
63
+ "<|af|>": 50327,
64
+ "<|am|>": 50334,
65
+ "<|ar|>": 50272,
66
+ "<|as|>": 50350,
67
+ "<|az|>": 50304,
68
+ "<|ba|>": 50355,
69
+ "<|be|>": 50330,
70
+ "<|bg|>": 50292,
71
+ "<|bn|>": 50302,
72
+ "<|bo|>": 50347,
73
+ "<|br|>": 50309,
74
+ "<|bs|>": 50315,
75
+ "<|ca|>": 50270,
76
+ "<|cs|>": 50283,
77
+ "<|cy|>": 50297,
78
+ "<|da|>": 50285,
79
+ "<|de|>": 50261,
80
+ "<|el|>": 50281,
81
+ "<|en|>": 50259,
82
+ "<|es|>": 50262,
83
+ "<|et|>": 50307,
84
+ "<|eu|>": 50310,
85
+ "<|fa|>": 50300,
86
+ "<|fi|>": 50277,
87
+ "<|fo|>": 50338,
88
+ "<|fr|>": 50265,
89
+ "<|gl|>": 50319,
90
+ "<|gu|>": 50333,
91
+ "<|haw|>": 50352,
92
+ "<|ha|>": 50354,
93
+ "<|he|>": 50279,
94
+ "<|hi|>": 50276,
95
+ "<|hr|>": 50291,
96
+ "<|ht|>": 50339,
97
+ "<|hu|>": 50286,
98
+ "<|hy|>": 50312,
99
+ "<|id|>": 50275,
100
+ "<|is|>": 50311,
101
+ "<|it|>": 50274,
102
+ "<|ja|>": 50266,
103
+ "<|jw|>": 50356,
104
+ "<|ka|>": 50329,
105
+ "<|kk|>": 50316,
106
+ "<|km|>": 50323,
107
+ "<|kn|>": 50306,
108
+ "<|ko|>": 50264,
109
+ "<|la|>": 50294,
110
+ "<|lb|>": 50345,
111
+ "<|ln|>": 50353,
112
+ "<|lo|>": 50336,
113
+ "<|lt|>": 50293,
114
+ "<|lv|>": 50301,
115
+ "<|mg|>": 50349,
116
+ "<|mi|>": 50295,
117
+ "<|mk|>": 50308,
118
+ "<|ml|>": 50296,
119
+ "<|mn|>": 50314,
120
+ "<|mr|>": 50320,
121
+ "<|ms|>": 50282,
122
+ "<|mt|>": 50343,
123
+ "<|my|>": 50346,
124
+ "<|ne|>": 50313,
125
+ "<|nl|>": 50271,
126
+ "<|nn|>": 50342,
127
+ "<|no|>": 50288,
128
+ "<|oc|>": 50328,
129
+ "<|pa|>": 50321,
130
+ "<|pl|>": 50269,
131
+ "<|ps|>": 50340,
132
+ "<|pt|>": 50267,
133
+ "<|ro|>": 50284,
134
+ "<|ru|>": 50263,
135
+ "<|sa|>": 50344,
136
+ "<|sd|>": 50332,
137
+ "<|si|>": 50322,
138
+ "<|sk|>": 50298,
139
+ "<|sl|>": 50305,
140
+ "<|sn|>": 50324,
141
+ "<|so|>": 50326,
142
+ "<|sq|>": 50317,
143
+ "<|sr|>": 50303,
144
+ "<|su|>": 50357,
145
+ "<|sv|>": 50273,
146
+ "<|sw|>": 50318,
147
+ "<|ta|>": 50287,
148
+ "<|te|>": 50299,
149
+ "<|tg|>": 50331,
150
+ "<|th|>": 50289,
151
+ "<|tk|>": 50341,
152
+ "<|tl|>": 50348,
153
+ "<|tr|>": 50268,
154
+ "<|tt|>": 50351,
155
+ "<|uk|>": 50280,
156
+ "<|ur|>": 50290,
157
+ "<|uz|>": 50337,
158
+ "<|vi|>": 50278,
159
+ "<|yi|>": 50335,
160
+ "<|yo|>": 50325,
161
+ "<|zh|>": 50260
162
+ },
163
+ "max_initial_timestamp_index": 1,
164
+ "max_length": 448,
165
+ "no_timestamps_token_id": 50363,
166
+ "pad_token_id": 50257,
167
+ "return_timestamps": false,
168
+ "suppress_tokens": [
169
+ 1,
170
+ 2,
171
+ 7,
172
+ 8,
173
+ 9,
174
+ 10,
175
+ 14,
176
+ 25,
177
+ 26,
178
+ 27,
179
+ 28,
180
+ 29,
181
+ 31,
182
+ 58,
183
+ 59,
184
+ 60,
185
+ 61,
186
+ 62,
187
+ 63,
188
+ 90,
189
+ 91,
190
+ 92,
191
+ 93,
192
+ 359,
193
+ 503,
194
+ 522,
195
+ 542,
196
+ 873,
197
+ 893,
198
+ 902,
199
+ 918,
200
+ 922,
201
+ 931,
202
+ 1350,
203
+ 1853,
204
+ 1982,
205
+ 2460,
206
+ 2627,
207
+ 3246,
208
+ 3253,
209
+ 3268,
210
+ 3536,
211
+ 3846,
212
+ 3961,
213
+ 4183,
214
+ 4667,
215
+ 6585,
216
+ 6647,
217
+ 7273,
218
+ 9061,
219
+ 9383,
220
+ 10428,
221
+ 10929,
222
+ 11938,
223
+ 12033,
224
+ 12331,
225
+ 12562,
226
+ 13793,
227
+ 14157,
228
+ 14635,
229
+ 15265,
230
+ 15618,
231
+ 16553,
232
+ 16604,
233
+ 18362,
234
+ 18956,
235
+ 20075,
236
+ 21675,
237
+ 22520,
238
+ 26130,
239
+ 26161,
240
+ 26435,
241
+ 28279,
242
+ 29464,
243
+ 31650,
244
+ 32302,
245
+ 32470,
246
+ 36865,
247
+ 42863,
248
+ 47425,
249
+ 49870,
250
+ 50254,
251
+ 50258,
252
+ 50358,
253
+ 50359,
254
+ 50360,
255
+ 50361,
256
+ 50362
257
+ ],
258
+ "task_to_id": {
259
+ "transcribe": 50359,
260
+ "translate": 50358
261
+ },
262
+ "transformers_version": "4.37.0.dev0"
263
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2436b0c1112d594abbceb6bd9a2ad19da82ecc9ccdd82d78bca07a5717cb75c
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e4962c2fc098ed718d673eba4bf9c1472086ffdb9c3a1ad02742dc4c0b5329
3
  size 966995080