FelixK7 commited on
Commit
7f275b7
1 Parent(s): 67bd71c

End of training

Browse files
Files changed (3) hide show
  1. README.md +107 -0
  2. generation_config.json +249 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - lv
5
+ license: apache-2.0
6
+ base_model: openai/whisper-medium
7
+ tags:
8
+ - hf-asr-leaderboard
9
+ - generated_from_trainer
10
+ datasets:
11
+ - mozilla-foundation/common_voice_17_0
12
+ metrics:
13
+ - wer
14
+ model-index:
15
+ - name: Whisper medium LV - Felikss Kleins
16
+ results:
17
+ - task:
18
+ name: Automatic Speech Recognition
19
+ type: automatic-speech-recognition
20
+ dataset:
21
+ name: Common Voice 17.0
22
+ type: mozilla-foundation/common_voice_17_0
23
+ config: lv
24
+ split: None
25
+ args: 'config: lv, split: test'
26
+ metrics:
27
+ - name: Wer
28
+ type: wer
29
+ value: 67.95180722891565
30
+ ---
31
+
32
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
33
+ should probably proofread and complete it, then remove this comment. -->
34
+
35
+ # Whisper medium LV - Felikss Kleins
36
+
37
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 17.0 dataset.
38
+ It achieves the following results on the evaluation set:
39
+ - Loss: 1.1313
40
+ - Wer: 67.9518
41
+
42
+ ## Model description
43
+
44
+ More information needed
45
+
46
+ ## Intended uses & limitations
47
+
48
+ More information needed
49
+
50
+ ## Training and evaluation data
51
+
52
+ More information needed
53
+
54
+ ## Training procedure
55
+
56
+ ### Training hyperparameters
57
+
58
+ The following hyperparameters were used during training:
59
+ - learning_rate: 5e-06
60
+ - train_batch_size: 6
61
+ - eval_batch_size: 16
62
+ - seed: 42
63
+ - gradient_accumulation_steps: 2
64
+ - total_train_batch_size: 12
65
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
66
+ - lr_scheduler_type: linear
67
+ - lr_scheduler_warmup_steps: 500
68
+ - training_steps: 5000
69
+ - mixed_precision_training: Native AMP
70
+
71
+ ### Training results
72
+
73
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
74
+ |:-------------:|:--------:|:----:|:---------------:|:-------:|
75
+ | No log | 23.0009 | 200 | 0.9920 | 47.2289 |
76
+ | 1.4829 | 47.0001 | 400 | 0.7982 | 48.9157 |
77
+ | 0.046 | 70.001 | 600 | 0.9576 | 51.3253 |
78
+ | 0.011 | 94.0002 | 800 | 0.9129 | 49.3976 |
79
+ | 0.0057 | 117.0011 | 1000 | 0.9789 | 51.3253 |
80
+ | 0.0057 | 141.0003 | 1200 | 1.0248 | 51.8072 |
81
+ | 0.005 | 164.0012 | 1400 | 1.0504 | 53.4940 |
82
+ | 0.0021 | 188.0004 | 1600 | 1.0447 | 67.9518 |
83
+ | 0.0015 | 211.0013 | 1800 | 1.0433 | 73.2530 |
84
+ | 0.0012 | 235.0005 | 2000 | 1.0646 | 55.1807 |
85
+ | 0.0012 | 258.0014 | 2200 | 1.1244 | 53.7349 |
86
+ | 0.0007 | 282.0006 | 2400 | 1.1156 | 59.5181 |
87
+ | 0.0006 | 305.0015 | 2600 | 1.1081 | 58.5542 |
88
+ | 0.0009 | 329.0007 | 2800 | 1.0342 | 54.4578 |
89
+ | 0.0006 | 352.0016 | 3000 | 1.0215 | 50.8434 |
90
+ | 0.0006 | 376.0008 | 3200 | 1.0619 | 56.6265 |
91
+ | 0.0004 | 399.0017 | 3400 | 1.1083 | 55.4217 |
92
+ | 0.0003 | 423.0009 | 3600 | 1.0970 | 56.8675 |
93
+ | 0.0006 | 447.0001 | 3800 | 1.1047 | 59.0361 |
94
+ | 0.0003 | 470.001 | 4000 | 1.1033 | 56.1446 |
95
+ | 0.0003 | 494.0002 | 4200 | 1.1003 | 57.5904 |
96
+ | 0.0002 | 517.0011 | 4400 | 1.1133 | 68.4337 |
97
+ | 0.0002 | 541.0003 | 4600 | 1.1146 | 69.3976 |
98
+ | 0.0001 | 564.0012 | 4800 | 1.1267 | 69.8795 |
99
+ | 0.0001 | 588.0004 | 5000 | 1.1313 | 67.9518 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.45.0.dev0
105
+ - Pytorch 2.0.1
106
+ - Datasets 3.0.0
107
+ - 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
+ "max_initial_timestamp_index": 50,
148
+ "max_length": 448,
149
+ "no_timestamps_token_id": 50363,
150
+ "pad_token_id": 50257,
151
+ "prev_sot_token_id": 50361,
152
+ "return_timestamps": false,
153
+ "suppress_tokens": [
154
+ 1,
155
+ 2,
156
+ 7,
157
+ 8,
158
+ 9,
159
+ 10,
160
+ 14,
161
+ 25,
162
+ 26,
163
+ 27,
164
+ 28,
165
+ 29,
166
+ 31,
167
+ 58,
168
+ 59,
169
+ 60,
170
+ 61,
171
+ 62,
172
+ 63,
173
+ 90,
174
+ 91,
175
+ 92,
176
+ 93,
177
+ 359,
178
+ 503,
179
+ 522,
180
+ 542,
181
+ 873,
182
+ 893,
183
+ 902,
184
+ 918,
185
+ 922,
186
+ 931,
187
+ 1350,
188
+ 1853,
189
+ 1982,
190
+ 2460,
191
+ 2627,
192
+ 3246,
193
+ 3253,
194
+ 3268,
195
+ 3536,
196
+ 3846,
197
+ 3961,
198
+ 4183,
199
+ 4667,
200
+ 6585,
201
+ 6647,
202
+ 7273,
203
+ 9061,
204
+ 9383,
205
+ 10428,
206
+ 10929,
207
+ 11938,
208
+ 12033,
209
+ 12331,
210
+ 12562,
211
+ 13793,
212
+ 14157,
213
+ 14635,
214
+ 15265,
215
+ 15618,
216
+ 16553,
217
+ 16604,
218
+ 18362,
219
+ 18956,
220
+ 20075,
221
+ 21675,
222
+ 22520,
223
+ 26130,
224
+ 26161,
225
+ 26435,
226
+ 28279,
227
+ 29464,
228
+ 31650,
229
+ 32302,
230
+ 32470,
231
+ 36865,
232
+ 42863,
233
+ 47425,
234
+ 49870,
235
+ 50254,
236
+ 50258,
237
+ 50358,
238
+ 50359,
239
+ 50360,
240
+ 50361,
241
+ 50362
242
+ ],
243
+ "task_to_id": {
244
+ "transcribe": 50359,
245
+ "translate": 50358
246
+ },
247
+ "transformers_version": "4.45.0.dev0",
248
+ "use_cache": false
249
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:478328280a7e8d26c726752c8723a4fb59a8723fe706976b91f4b149dff3c1ca
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e662f93673880fee70c91e367fb9db1577399c32375b6402a33d69c97799874f
3
  size 3055544304