mirodil commited on
Commit
71b44da
1 Parent(s): 6caf399

End of training

Browse files
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-uzbek
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-uzbek
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: 0.6155
21
+ - Wer Ortho: 54.5846
22
+ - Wer: 42.7596
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 1e-05
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 16
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: constant_with_warmup
47
+ - lr_scheduler_warmup_steps: 50
48
+ - training_steps: 500
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
55
+ | 0.7298 | 0.27 | 500 | 0.6155 | 54.5846 | 42.7596 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.35.2
61
+ - Pytorch 2.1.0+cu118
62
+ - Datasets 2.15.0
63
+ - Tokenizers 0.15.0
generation_config.json ADDED
@@ -0,0 +1,269 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 50337
55
+ ],
56
+ [
57
+ 2,
58
+ 50359
59
+ ],
60
+ [
61
+ 3,
62
+ 50363
63
+ ]
64
+ ],
65
+ "is_multilingual": true,
66
+ "lang_to_id": {
67
+ "<|af|>": 50327,
68
+ "<|am|>": 50334,
69
+ "<|ar|>": 50272,
70
+ "<|as|>": 50350,
71
+ "<|az|>": 50304,
72
+ "<|ba|>": 50355,
73
+ "<|be|>": 50330,
74
+ "<|bg|>": 50292,
75
+ "<|bn|>": 50302,
76
+ "<|bo|>": 50347,
77
+ "<|br|>": 50309,
78
+ "<|bs|>": 50315,
79
+ "<|ca|>": 50270,
80
+ "<|cs|>": 50283,
81
+ "<|cy|>": 50297,
82
+ "<|da|>": 50285,
83
+ "<|de|>": 50261,
84
+ "<|el|>": 50281,
85
+ "<|en|>": 50259,
86
+ "<|es|>": 50262,
87
+ "<|et|>": 50307,
88
+ "<|eu|>": 50310,
89
+ "<|fa|>": 50300,
90
+ "<|fi|>": 50277,
91
+ "<|fo|>": 50338,
92
+ "<|fr|>": 50265,
93
+ "<|gl|>": 50319,
94
+ "<|gu|>": 50333,
95
+ "<|haw|>": 50352,
96
+ "<|ha|>": 50354,
97
+ "<|he|>": 50279,
98
+ "<|hi|>": 50276,
99
+ "<|hr|>": 50291,
100
+ "<|ht|>": 50339,
101
+ "<|hu|>": 50286,
102
+ "<|hy|>": 50312,
103
+ "<|id|>": 50275,
104
+ "<|is|>": 50311,
105
+ "<|it|>": 50274,
106
+ "<|ja|>": 50266,
107
+ "<|jw|>": 50356,
108
+ "<|ka|>": 50329,
109
+ "<|kk|>": 50316,
110
+ "<|km|>": 50323,
111
+ "<|kn|>": 50306,
112
+ "<|ko|>": 50264,
113
+ "<|la|>": 50294,
114
+ "<|lb|>": 50345,
115
+ "<|ln|>": 50353,
116
+ "<|lo|>": 50336,
117
+ "<|lt|>": 50293,
118
+ "<|lv|>": 50301,
119
+ "<|mg|>": 50349,
120
+ "<|mi|>": 50295,
121
+ "<|mk|>": 50308,
122
+ "<|ml|>": 50296,
123
+ "<|mn|>": 50314,
124
+ "<|mr|>": 50320,
125
+ "<|ms|>": 50282,
126
+ "<|mt|>": 50343,
127
+ "<|my|>": 50346,
128
+ "<|ne|>": 50313,
129
+ "<|nl|>": 50271,
130
+ "<|nn|>": 50342,
131
+ "<|no|>": 50288,
132
+ "<|oc|>": 50328,
133
+ "<|pa|>": 50321,
134
+ "<|pl|>": 50269,
135
+ "<|ps|>": 50340,
136
+ "<|pt|>": 50267,
137
+ "<|ro|>": 50284,
138
+ "<|ru|>": 50263,
139
+ "<|sa|>": 50344,
140
+ "<|sd|>": 50332,
141
+ "<|si|>": 50322,
142
+ "<|sk|>": 50298,
143
+ "<|sl|>": 50305,
144
+ "<|sn|>": 50324,
145
+ "<|so|>": 50326,
146
+ "<|sq|>": 50317,
147
+ "<|sr|>": 50303,
148
+ "<|su|>": 50357,
149
+ "<|sv|>": 50273,
150
+ "<|sw|>": 50318,
151
+ "<|ta|>": 50287,
152
+ "<|te|>": 50299,
153
+ "<|tg|>": 50331,
154
+ "<|th|>": 50289,
155
+ "<|tk|>": 50341,
156
+ "<|tl|>": 50348,
157
+ "<|tr|>": 50268,
158
+ "<|tt|>": 50351,
159
+ "<|uk|>": 50280,
160
+ "<|ur|>": 50290,
161
+ "<|uz|>": 50337,
162
+ "<|vi|>": 50278,
163
+ "<|yi|>": 50335,
164
+ "<|yo|>": 50325,
165
+ "<|zh|>": 50260
166
+ },
167
+ "language": "uzbek",
168
+ "max_initial_timestamp_index": 1,
169
+ "max_length": 448,
170
+ "no_timestamps_token_id": 50363,
171
+ "pad_token_id": 50257,
172
+ "return_timestamps": false,
173
+ "suppress_tokens": [
174
+ 1,
175
+ 2,
176
+ 7,
177
+ 8,
178
+ 9,
179
+ 10,
180
+ 14,
181
+ 25,
182
+ 26,
183
+ 27,
184
+ 28,
185
+ 29,
186
+ 31,
187
+ 58,
188
+ 59,
189
+ 60,
190
+ 61,
191
+ 62,
192
+ 63,
193
+ 90,
194
+ 91,
195
+ 92,
196
+ 93,
197
+ 359,
198
+ 503,
199
+ 522,
200
+ 542,
201
+ 873,
202
+ 893,
203
+ 902,
204
+ 918,
205
+ 922,
206
+ 931,
207
+ 1350,
208
+ 1853,
209
+ 1982,
210
+ 2460,
211
+ 2627,
212
+ 3246,
213
+ 3253,
214
+ 3268,
215
+ 3536,
216
+ 3846,
217
+ 3961,
218
+ 4183,
219
+ 4667,
220
+ 6585,
221
+ 6647,
222
+ 7273,
223
+ 9061,
224
+ 9383,
225
+ 10428,
226
+ 10929,
227
+ 11938,
228
+ 12033,
229
+ 12331,
230
+ 12562,
231
+ 13793,
232
+ 14157,
233
+ 14635,
234
+ 15265,
235
+ 15618,
236
+ 16553,
237
+ 16604,
238
+ 18362,
239
+ 18956,
240
+ 20075,
241
+ 21675,
242
+ 22520,
243
+ 26130,
244
+ 26161,
245
+ 26435,
246
+ 28279,
247
+ 29464,
248
+ 31650,
249
+ 32302,
250
+ 32470,
251
+ 36865,
252
+ 42863,
253
+ 47425,
254
+ 49870,
255
+ 50254,
256
+ 50258,
257
+ 50358,
258
+ 50359,
259
+ 50360,
260
+ 50361,
261
+ 50362
262
+ ],
263
+ "task": "transcribe",
264
+ "task_to_id": {
265
+ "transcribe": 50359,
266
+ "translate": 50358
267
+ },
268
+ "transformers_version": "4.35.2"
269
+ }
runs/Nov21_23-16-16_3b1c19b100f9/events.out.tfevents.1700608583.3b1c19b100f9.716.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6e67500d5abc5e85c352e2e30ac9f5794035d30d673366f10709f729bfde7a
3
+ size 9856
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7106cf3cc8e47a6ac97332079bd0f2f446cd5373204d412386fcc29491660ab5
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb40810a6d02a0d3d1e2c4743e81d12f35e60d0d9b0e03d6cefd192a0830aead
3
  size 4728