ymoslem commited on
Commit
b06e22c
1 Parent(s): 98da9c1

Model save

Browse files
Files changed (2) hide show
  1. README.md +50 -0
  2. generation_config.json +249 -0
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: openai/whisper-medium
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: whisper-medium-ga2en-v5.3.2-19k-r
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # whisper-medium-ga2en-v5.3.2-19k-r
15
+
16
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.0001
36
+ - train_batch_size: 16
37
+ - eval_batch_size: 16
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - lr_scheduler_warmup_ratio: 0.03
42
+ - training_steps: 19000
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Framework versions
46
+
47
+ - Transformers 4.41.2
48
+ - Pytorch 2.2.0+cu121
49
+ - Datasets 2.20.0
50
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 13,
5
+ 15
6
+ ],
7
+ [
8
+ 15,
9
+ 4
10
+ ],
11
+ [
12
+ 15,
13
+ 15
14
+ ],
15
+ [
16
+ 16,
17
+ 1
18
+ ],
19
+ [
20
+ 20,
21
+ 0
22
+ ],
23
+ [
24
+ 23,
25
+ 4
26
+ ]
27
+ ],
28
+ "begin_suppress_tokens": [
29
+ 220,
30
+ 50257
31
+ ],
32
+ "bos_token_id": 50257,
33
+ "decoder_start_token_id": 50258,
34
+ "eos_token_id": 50257,
35
+ "forced_decoder_ids": [
36
+ [
37
+ 1,
38
+ null
39
+ ],
40
+ [
41
+ 2,
42
+ 50359
43
+ ]
44
+ ],
45
+ "is_multilingual": true,
46
+ "lang_to_id": {
47
+ "<|af|>": 50327,
48
+ "<|am|>": 50334,
49
+ "<|ar|>": 50272,
50
+ "<|as|>": 50350,
51
+ "<|az|>": 50304,
52
+ "<|ba|>": 50355,
53
+ "<|be|>": 50330,
54
+ "<|bg|>": 50292,
55
+ "<|bn|>": 50302,
56
+ "<|bo|>": 50347,
57
+ "<|br|>": 50309,
58
+ "<|bs|>": 50315,
59
+ "<|ca|>": 50270,
60
+ "<|cs|>": 50283,
61
+ "<|cy|>": 50297,
62
+ "<|da|>": 50285,
63
+ "<|de|>": 50261,
64
+ "<|el|>": 50281,
65
+ "<|en|>": 50259,
66
+ "<|es|>": 50262,
67
+ "<|et|>": 50307,
68
+ "<|eu|>": 50310,
69
+ "<|fa|>": 50300,
70
+ "<|fi|>": 50277,
71
+ "<|fo|>": 50338,
72
+ "<|fr|>": 50265,
73
+ "<|gl|>": 50319,
74
+ "<|gu|>": 50333,
75
+ "<|haw|>": 50352,
76
+ "<|ha|>": 50354,
77
+ "<|he|>": 50279,
78
+ "<|hi|>": 50276,
79
+ "<|hr|>": 50291,
80
+ "<|ht|>": 50339,
81
+ "<|hu|>": 50286,
82
+ "<|hy|>": 50312,
83
+ "<|id|>": 50275,
84
+ "<|is|>": 50311,
85
+ "<|it|>": 50274,
86
+ "<|ja|>": 50266,
87
+ "<|jw|>": 50356,
88
+ "<|ka|>": 50329,
89
+ "<|kk|>": 50316,
90
+ "<|km|>": 50323,
91
+ "<|kn|>": 50306,
92
+ "<|ko|>": 50264,
93
+ "<|la|>": 50294,
94
+ "<|lb|>": 50345,
95
+ "<|ln|>": 50353,
96
+ "<|lo|>": 50336,
97
+ "<|lt|>": 50293,
98
+ "<|lv|>": 50301,
99
+ "<|mg|>": 50349,
100
+ "<|mi|>": 50295,
101
+ "<|mk|>": 50308,
102
+ "<|ml|>": 50296,
103
+ "<|mn|>": 50314,
104
+ "<|mr|>": 50320,
105
+ "<|ms|>": 50282,
106
+ "<|mt|>": 50343,
107
+ "<|my|>": 50346,
108
+ "<|ne|>": 50313,
109
+ "<|nl|>": 50271,
110
+ "<|nn|>": 50342,
111
+ "<|no|>": 50288,
112
+ "<|oc|>": 50328,
113
+ "<|pa|>": 50321,
114
+ "<|pl|>": 50269,
115
+ "<|ps|>": 50340,
116
+ "<|pt|>": 50267,
117
+ "<|ro|>": 50284,
118
+ "<|ru|>": 50263,
119
+ "<|sa|>": 50344,
120
+ "<|sd|>": 50332,
121
+ "<|si|>": 50322,
122
+ "<|sk|>": 50298,
123
+ "<|sl|>": 50305,
124
+ "<|sn|>": 50324,
125
+ "<|so|>": 50326,
126
+ "<|sq|>": 50317,
127
+ "<|sr|>": 50303,
128
+ "<|su|>": 50357,
129
+ "<|sv|>": 50273,
130
+ "<|sw|>": 50318,
131
+ "<|ta|>": 50287,
132
+ "<|te|>": 50299,
133
+ "<|tg|>": 50331,
134
+ "<|th|>": 50289,
135
+ "<|tk|>": 50341,
136
+ "<|tl|>": 50348,
137
+ "<|tr|>": 50268,
138
+ "<|tt|>": 50351,
139
+ "<|uk|>": 50280,
140
+ "<|ur|>": 50290,
141
+ "<|uz|>": 50337,
142
+ "<|vi|>": 50278,
143
+ "<|yi|>": 50335,
144
+ "<|yo|>": 50325,
145
+ "<|zh|>": 50260
146
+ },
147
+ "language": "en",
148
+ "max_initial_timestamp_index": 50,
149
+ "max_length": 448,
150
+ "no_timestamps_token_id": 50363,
151
+ "pad_token_id": 50257,
152
+ "prev_sot_token_id": 50361,
153
+ "return_timestamps": false,
154
+ "suppress_tokens": [
155
+ 1,
156
+ 2,
157
+ 7,
158
+ 8,
159
+ 9,
160
+ 10,
161
+ 14,
162
+ 25,
163
+ 26,
164
+ 27,
165
+ 28,
166
+ 29,
167
+ 31,
168
+ 58,
169
+ 59,
170
+ 60,
171
+ 61,
172
+ 62,
173
+ 63,
174
+ 90,
175
+ 91,
176
+ 92,
177
+ 93,
178
+ 359,
179
+ 503,
180
+ 522,
181
+ 542,
182
+ 873,
183
+ 893,
184
+ 902,
185
+ 918,
186
+ 922,
187
+ 931,
188
+ 1350,
189
+ 1853,
190
+ 1982,
191
+ 2460,
192
+ 2627,
193
+ 3246,
194
+ 3253,
195
+ 3268,
196
+ 3536,
197
+ 3846,
198
+ 3961,
199
+ 4183,
200
+ 4667,
201
+ 6585,
202
+ 6647,
203
+ 7273,
204
+ 9061,
205
+ 9383,
206
+ 10428,
207
+ 10929,
208
+ 11938,
209
+ 12033,
210
+ 12331,
211
+ 12562,
212
+ 13793,
213
+ 14157,
214
+ 14635,
215
+ 15265,
216
+ 15618,
217
+ 16553,
218
+ 16604,
219
+ 18362,
220
+ 18956,
221
+ 20075,
222
+ 21675,
223
+ 22520,
224
+ 26130,
225
+ 26161,
226
+ 26435,
227
+ 28279,
228
+ 29464,
229
+ 31650,
230
+ 32302,
231
+ 32470,
232
+ 36865,
233
+ 42863,
234
+ 47425,
235
+ 49870,
236
+ 50254,
237
+ 50258,
238
+ 50358,
239
+ 50359,
240
+ 50360,
241
+ 50361,
242
+ 50362
243
+ ],
244
+ "task_to_id": {
245
+ "transcribe": 50359,
246
+ "translate": 50358
247
+ },
248
+ "transformers_version": "4.41.2"
249
+ }