zuazo commited on
Commit
29b57ea
·
verified ·
1 Parent(s): e008409

Model save

Browse files
README.md ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: openai/whisper-large-v3
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - common_voice_17_0
9
+ metrics:
10
+ - wer
11
+ model-index:
12
+ - name: openai/whisper-large-v3
13
+ results:
14
+ - task:
15
+ name: Automatic Speech Recognition
16
+ type: automatic-speech-recognition
17
+ dataset:
18
+ name: common_voice_17_0
19
+ type: common_voice_17_0
20
+ config: eu
21
+ split: test
22
+ args: eu
23
+ metrics:
24
+ - name: Wer
25
+ type: wer
26
+ value: 6.456814100919785
27
+ ---
28
+
29
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
+ should probably proofread and complete it, then remove this comment. -->
31
+
32
+ # openai/whisper-large-v3
33
+
34
+ This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the common_voice_17_0 dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.2636
37
+ - Wer: 6.4568
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 3.75e-05
57
+ - train_batch_size: 32
58
+ - eval_batch_size: 16
59
+ - seed: 42
60
+ - gradient_accumulation_steps: 2
61
+ - total_train_batch_size: 64
62
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_steps: 500
65
+ - training_steps: 40000
66
+ - mixed_precision_training: Native AMP
67
+
68
+ ### Training results
69
+
70
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
71
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|
72
+ | 0.0674 | 2.3474 | 1000 | 0.1613 | 9.7732 |
73
+ | 0.0299 | 4.6948 | 2000 | 0.1633 | 8.9771 |
74
+ | 0.0164 | 7.0423 | 3000 | 0.1828 | 8.6381 |
75
+ | 0.0098 | 9.3897 | 4000 | 0.1870 | 8.2524 |
76
+ | 0.0105 | 11.7371 | 5000 | 0.1912 | 8.4146 |
77
+ | 0.0085 | 14.0845 | 6000 | 0.2029 | 8.5914 |
78
+ | 0.0076 | 16.4319 | 7000 | 0.2084 | 8.1296 |
79
+ | 0.0059 | 18.7793 | 8000 | 0.2028 | 8.1003 |
80
+ | 0.0059 | 21.1268 | 9000 | 0.2066 | 8.3404 |
81
+ | 0.0049 | 23.4742 | 10000 | 0.2154 | 8.3972 |
82
+ | 0.0044 | 25.8216 | 11000 | 0.2136 | 8.0087 |
83
+ | 0.0012 | 28.1690 | 12000 | 0.2111 | 7.3116 |
84
+ | 0.0038 | 30.5164 | 13000 | 0.2219 | 8.1471 |
85
+ | 0.0025 | 32.8638 | 14000 | 0.2155 | 7.6679 |
86
+ | 0.0021 | 35.2113 | 15000 | 0.2239 | 7.4893 |
87
+ | 0.0021 | 37.5587 | 16000 | 0.2277 | 7.8337 |
88
+ | 0.0017 | 39.9061 | 17000 | 0.2254 | 7.8108 |
89
+ | 0.0012 | 42.2535 | 18000 | 0.2247 | 7.2914 |
90
+ | 0.0021 | 44.6009 | 19000 | 0.2301 | 8.0005 |
91
+ | 0.0016 | 46.9484 | 20000 | 0.2346 | 7.7568 |
92
+ | 0.001 | 49.2958 | 21000 | 0.2283 | 7.3940 |
93
+ | 0.0021 | 51.6432 | 22000 | 0.2297 | 7.5589 |
94
+ | 0.0013 | 53.9906 | 23000 | 0.2324 | 7.6029 |
95
+ | 0.0004 | 56.3380 | 24000 | 0.2333 | 6.9369 |
96
+ | 0.0003 | 58.6854 | 25000 | 0.2254 | 6.8114 |
97
+ | 0.0016 | 61.0329 | 26000 | 0.2393 | 7.6688 |
98
+ | 0.0001 | 63.3803 | 27000 | 0.2279 | 6.8819 |
99
+ | 0.0 | 65.7277 | 28000 | 0.2320 | 6.8269 |
100
+ | 0.0 | 68.0751 | 29000 | 0.2421 | 6.5832 |
101
+ | 0.0 | 70.4225 | 30000 | 0.2481 | 6.4770 |
102
+ | 0.0 | 72.7700 | 31000 | 0.2532 | 6.4000 |
103
+ | 0.0 | 75.1174 | 32000 | 0.2570 | 6.3863 |
104
+ | 0.0011 | 77.4648 | 33000 | 0.2388 | 7.2392 |
105
+ | 0.0 | 79.8122 | 34000 | 0.2403 | 6.8223 |
106
+ | 0.0 | 82.1596 | 35000 | 0.2477 | 6.6639 |
107
+ | 0.0 | 84.5070 | 36000 | 0.2528 | 6.6071 |
108
+ | 0.0001 | 86.8545 | 37000 | 0.2562 | 6.5503 |
109
+ | 0.0 | 89.2019 | 38000 | 0.2597 | 6.4971 |
110
+ | 0.0 | 91.5493 | 39000 | 0.2623 | 6.4632 |
111
+ | 0.0 | 93.8967 | 40000 | 0.2636 | 6.4568 |
112
+
113
+
114
+ ### Framework versions
115
+
116
+ - Transformers 4.52.3
117
+ - Pytorch 2.6.0+cu124
118
+ - Datasets 3.6.0
119
+ - Tokenizers 0.21.1
generation_config.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 7,
5
+ 0
6
+ ],
7
+ [
8
+ 10,
9
+ 17
10
+ ],
11
+ [
12
+ 12,
13
+ 18
14
+ ],
15
+ [
16
+ 13,
17
+ 12
18
+ ],
19
+ [
20
+ 16,
21
+ 1
22
+ ],
23
+ [
24
+ 17,
25
+ 14
26
+ ],
27
+ [
28
+ 19,
29
+ 11
30
+ ],
31
+ [
32
+ 21,
33
+ 4
34
+ ],
35
+ [
36
+ 24,
37
+ 1
38
+ ],
39
+ [
40
+ 25,
41
+ 6
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
+ 50360
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
+ "<|yue|>": 50358,
162
+ "<|zh|>": 50260
163
+ },
164
+ "max_initial_timestamp_index": 50,
165
+ "max_length": 448,
166
+ "no_timestamps_token_id": 50364,
167
+ "pad_token_id": 50257,
168
+ "prev_sot_token_id": 50362,
169
+ "return_timestamps": false,
170
+ "suppress_tokens": [
171
+ 1,
172
+ 2,
173
+ 7,
174
+ 8,
175
+ 9,
176
+ 10,
177
+ 14,
178
+ 25,
179
+ 26,
180
+ 27,
181
+ 28,
182
+ 29,
183
+ 31,
184
+ 58,
185
+ 59,
186
+ 60,
187
+ 61,
188
+ 62,
189
+ 63,
190
+ 90,
191
+ 91,
192
+ 92,
193
+ 93,
194
+ 359,
195
+ 503,
196
+ 522,
197
+ 542,
198
+ 873,
199
+ 893,
200
+ 902,
201
+ 918,
202
+ 922,
203
+ 931,
204
+ 1350,
205
+ 1853,
206
+ 1982,
207
+ 2460,
208
+ 2627,
209
+ 3246,
210
+ 3253,
211
+ 3268,
212
+ 3536,
213
+ 3846,
214
+ 3961,
215
+ 4183,
216
+ 4667,
217
+ 6585,
218
+ 6647,
219
+ 7273,
220
+ 9061,
221
+ 9383,
222
+ 10428,
223
+ 10929,
224
+ 11938,
225
+ 12033,
226
+ 12331,
227
+ 12562,
228
+ 13793,
229
+ 14157,
230
+ 14635,
231
+ 15265,
232
+ 15618,
233
+ 16553,
234
+ 16604,
235
+ 18362,
236
+ 18956,
237
+ 20075,
238
+ 21675,
239
+ 22520,
240
+ 26130,
241
+ 26161,
242
+ 26435,
243
+ 28279,
244
+ 29464,
245
+ 31650,
246
+ 32302,
247
+ 32470,
248
+ 36865,
249
+ 42863,
250
+ 47425,
251
+ 49870,
252
+ 50254,
253
+ 50258,
254
+ 50359,
255
+ 50360,
256
+ 50361,
257
+ 50362,
258
+ 50363
259
+ ],
260
+ "task_to_id": {
261
+ "transcribe": 50360,
262
+ "translate": 50359
263
+ },
264
+ "transformers_version": "4.52.3"
265
+ }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5f2e33052437c5b6939a2714e544c5efae3573a23c4e5b92793aa7f976f0b85
3
  size 4993448880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3338144eadf495d9fd9a90efead3a426117f627e8ea00506e0b3e38fdd96d707
3
  size 4993448880
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae81d18eed486d16f8a056dc72e9c3471fb0239891bb5f4429bb8897c905bb68
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92adee69b05db1cb3c489360dcc35b70e0d75af2b1a53c741eeecc2cf1f658c4
3
  size 1180663192