Cristhian2430 commited on
Commit
1020b74
1 Parent(s): 66c5660

End of training

Browse files
Files changed (2) hide show
  1. README.md +66 -0
  2. generation_config.json +259 -0
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - es
4
+ license: apache-2.0
5
+ base_model: openai/whisper-large
6
+ tags:
7
+ - hf-asr-leaderboard
8
+ - generated_from_trainer
9
+ metrics:
10
+ - wer
11
+ model-index:
12
+ - name: Whisper Large SEIN - COES SEIN
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # Whisper Large SEIN - COES SEIN
20
+
21
+ This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the SEIN COES dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.2948
24
+ - Wer: 70.8908
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
+ - learning_rate: 1e-05
44
+ - train_batch_size: 1
45
+ - eval_batch_size: 8
46
+ - seed: 42
47
+ - gradient_accumulation_steps: 4
48
+ - total_train_batch_size: 4
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_steps: 500
52
+ - training_steps: 100
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
57
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
58
+ | 1.3416 | 5.06 | 100 | 1.2948 | 70.8908 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.34.0.dev0
64
+ - Pytorch 2.0.1+cu118
65
+ - Datasets 2.14.5
66
+ - Tokenizers 0.13.3
generation_config.json ADDED
@@ -0,0 +1,259 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 9,
5
+ 19
6
+ ],
7
+ [
8
+ 11,
9
+ 2
10
+ ],
11
+ [
12
+ 11,
13
+ 4
14
+ ],
15
+ [
16
+ 11,
17
+ 17
18
+ ],
19
+ [
20
+ 22,
21
+ 7
22
+ ],
23
+ [
24
+ 22,
25
+ 11
26
+ ],
27
+ [
28
+ 22,
29
+ 17
30
+ ],
31
+ [
32
+ 23,
33
+ 2
34
+ ],
35
+ [
36
+ 23,
37
+ 15
38
+ ]
39
+ ],
40
+ "begin_suppress_tokens": [
41
+ 220,
42
+ 50257
43
+ ],
44
+ "bos_token_id": 50257,
45
+ "decoder_start_token_id": 50258,
46
+ "eos_token_id": 50257,
47
+ "forced_decoder_ids": [
48
+ [
49
+ 1,
50
+ null
51
+ ],
52
+ [
53
+ 2,
54
+ 50359
55
+ ]
56
+ ],
57
+ "is_multilingual": true,
58
+ "lang_to_id": {
59
+ "<|af|>": 50327,
60
+ "<|am|>": 50334,
61
+ "<|ar|>": 50272,
62
+ "<|as|>": 50350,
63
+ "<|az|>": 50304,
64
+ "<|ba|>": 50355,
65
+ "<|be|>": 50330,
66
+ "<|bg|>": 50292,
67
+ "<|bn|>": 50302,
68
+ "<|bo|>": 50347,
69
+ "<|br|>": 50309,
70
+ "<|bs|>": 50315,
71
+ "<|ca|>": 50270,
72
+ "<|cs|>": 50283,
73
+ "<|cy|>": 50297,
74
+ "<|da|>": 50285,
75
+ "<|de|>": 50261,
76
+ "<|el|>": 50281,
77
+ "<|en|>": 50259,
78
+ "<|es|>": 50262,
79
+ "<|et|>": 50307,
80
+ "<|eu|>": 50310,
81
+ "<|fa|>": 50300,
82
+ "<|fi|>": 50277,
83
+ "<|fo|>": 50338,
84
+ "<|fr|>": 50265,
85
+ "<|gl|>": 50319,
86
+ "<|gu|>": 50333,
87
+ "<|haw|>": 50352,
88
+ "<|ha|>": 50354,
89
+ "<|he|>": 50279,
90
+ "<|hi|>": 50276,
91
+ "<|hr|>": 50291,
92
+ "<|ht|>": 50339,
93
+ "<|hu|>": 50286,
94
+ "<|hy|>": 50312,
95
+ "<|id|>": 50275,
96
+ "<|is|>": 50311,
97
+ "<|it|>": 50274,
98
+ "<|ja|>": 50266,
99
+ "<|jw|>": 50356,
100
+ "<|ka|>": 50329,
101
+ "<|kk|>": 50316,
102
+ "<|km|>": 50323,
103
+ "<|kn|>": 50306,
104
+ "<|ko|>": 50264,
105
+ "<|la|>": 50294,
106
+ "<|lb|>": 50345,
107
+ "<|ln|>": 50353,
108
+ "<|lo|>": 50336,
109
+ "<|lt|>": 50293,
110
+ "<|lv|>": 50301,
111
+ "<|mg|>": 50349,
112
+ "<|mi|>": 50295,
113
+ "<|mk|>": 50308,
114
+ "<|ml|>": 50296,
115
+ "<|mn|>": 50314,
116
+ "<|mr|>": 50320,
117
+ "<|ms|>": 50282,
118
+ "<|mt|>": 50343,
119
+ "<|my|>": 50346,
120
+ "<|ne|>": 50313,
121
+ "<|nl|>": 50271,
122
+ "<|nn|>": 50342,
123
+ "<|no|>": 50288,
124
+ "<|oc|>": 50328,
125
+ "<|pa|>": 50321,
126
+ "<|pl|>": 50269,
127
+ "<|ps|>": 50340,
128
+ "<|pt|>": 50267,
129
+ "<|ro|>": 50284,
130
+ "<|ru|>": 50263,
131
+ "<|sa|>": 50344,
132
+ "<|sd|>": 50332,
133
+ "<|si|>": 50322,
134
+ "<|sk|>": 50298,
135
+ "<|sl|>": 50305,
136
+ "<|sn|>": 50324,
137
+ "<|so|>": 50326,
138
+ "<|sq|>": 50317,
139
+ "<|sr|>": 50303,
140
+ "<|su|>": 50357,
141
+ "<|sv|>": 50273,
142
+ "<|sw|>": 50318,
143
+ "<|ta|>": 50287,
144
+ "<|te|>": 50299,
145
+ "<|tg|>": 50331,
146
+ "<|th|>": 50289,
147
+ "<|tk|>": 50341,
148
+ "<|tl|>": 50348,
149
+ "<|tr|>": 50268,
150
+ "<|tt|>": 50351,
151
+ "<|uk|>": 50280,
152
+ "<|ur|>": 50290,
153
+ "<|uz|>": 50337,
154
+ "<|vi|>": 50278,
155
+ "<|yi|>": 50335,
156
+ "<|yo|>": 50325,
157
+ "<|zh|>": 50260
158
+ },
159
+ "max_initial_timestamp_index": 1,
160
+ "max_length": 448,
161
+ "no_timestamps_token_id": 50363,
162
+ "pad_token_id": 50257,
163
+ "return_timestamps": false,
164
+ "suppress_tokens": [
165
+ 1,
166
+ 2,
167
+ 7,
168
+ 8,
169
+ 9,
170
+ 10,
171
+ 14,
172
+ 25,
173
+ 26,
174
+ 27,
175
+ 28,
176
+ 29,
177
+ 31,
178
+ 58,
179
+ 59,
180
+ 60,
181
+ 61,
182
+ 62,
183
+ 63,
184
+ 90,
185
+ 91,
186
+ 92,
187
+ 93,
188
+ 359,
189
+ 503,
190
+ 522,
191
+ 542,
192
+ 873,
193
+ 893,
194
+ 902,
195
+ 918,
196
+ 922,
197
+ 931,
198
+ 1350,
199
+ 1853,
200
+ 1982,
201
+ 2460,
202
+ 2627,
203
+ 3246,
204
+ 3253,
205
+ 3268,
206
+ 3536,
207
+ 3846,
208
+ 3961,
209
+ 4183,
210
+ 4667,
211
+ 6585,
212
+ 6647,
213
+ 7273,
214
+ 9061,
215
+ 9383,
216
+ 10428,
217
+ 10929,
218
+ 11938,
219
+ 12033,
220
+ 12331,
221
+ 12562,
222
+ 13793,
223
+ 14157,
224
+ 14635,
225
+ 15265,
226
+ 15618,
227
+ 16553,
228
+ 16604,
229
+ 18362,
230
+ 18956,
231
+ 20075,
232
+ 21675,
233
+ 22520,
234
+ 26130,
235
+ 26161,
236
+ 26435,
237
+ 28279,
238
+ 29464,
239
+ 31650,
240
+ 32302,
241
+ 32470,
242
+ 36865,
243
+ 42863,
244
+ 47425,
245
+ 49870,
246
+ 50254,
247
+ 50258,
248
+ 50358,
249
+ 50359,
250
+ 50360,
251
+ 50361,
252
+ 50362
253
+ ],
254
+ "task_to_id": {
255
+ "transcribe": 50359,
256
+ "translate": 50358
257
+ },
258
+ "transformers_version": "4.34.0.dev0"
259
+ }