SamuelPfisterer1 commited on
Commit
7b8a22f
·
verified ·
1 Parent(s): 444f7bd

End of training

Browse files
README.md ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: openai/whisper-large-v3-turbo
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - fleurs
9
+ metrics:
10
+ - wer
11
+ model-index:
12
+ - name: whisper-large-v3-turbo-serbian-serbia
13
+ results:
14
+ - task:
15
+ name: Automatic Speech Recognition
16
+ type: automatic-speech-recognition
17
+ dataset:
18
+ name: fleurs
19
+ type: fleurs
20
+ config: sr_rs
21
+ split: None
22
+ args: sr_rs
23
+ metrics:
24
+ - name: Wer
25
+ type: wer
26
+ value: 18.343921455385505
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
+ # whisper-large-v3-turbo-serbian-serbia
33
+
34
+ This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the fleurs dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.5289
37
+ - Model Preparation Time: 0.0069
38
+ - Wer Ortho: 34.0354
39
+ - Wer: 18.3439
40
+
41
+ ## Model description
42
+
43
+ More information needed
44
+
45
+ ## Intended uses & limitations
46
+
47
+ More information needed
48
+
49
+ ## Training and evaluation data
50
+
51
+ More information needed
52
+
53
+ ## Training procedure
54
+
55
+ ### Training hyperparameters
56
+
57
+ The following hyperparameters were used during training:
58
+ - learning_rate: 1e-05
59
+ - train_batch_size: 64
60
+ - eval_batch_size: 64
61
+ - seed: 42
62
+ - gradient_accumulation_steps: 2
63
+ - total_train_batch_size: 128
64
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
65
+ - lr_scheduler_type: linear
66
+ - lr_scheduler_warmup_ratio: 0.06
67
+ - num_epochs: 1
68
+ - mixed_precision_training: Native AMP
69
+
70
+ ### Training results
71
+
72
+ | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Wer Ortho | Wer |
73
+ |:-------------:|:------:|:----:|:---------------:|:----------------------:|:---------:|:-------:|
74
+ | 0.1827 | 0.0263 | 32 | 0.8340 | 0.0069 | 36.3524 | 21.6142 |
75
+ | 0.1531 | 0.0527 | 64 | 0.6341 | 0.0069 | 36.4759 | 21.7225 |
76
+ | 0.1551 | 0.0790 | 96 | 0.6893 | 0.0069 | 36.0038 | 21.6647 |
77
+ | 0.1495 | 0.1054 | 128 | 0.5745 | 0.0069 | 35.4518 | 21.2388 |
78
+ | 0.1388 | 0.1317 | 160 | 0.5572 | 0.0069 | 35.5680 | 20.5241 |
79
+ | 0.1359 | 0.1581 | 192 | 0.6313 | 0.0069 | 36.2217 | 20.6974 |
80
+ | 0.138 | 0.1844 | 224 | 0.5451 | 0.0069 | 35.9384 | 20.4014 |
81
+ | 0.1332 | 0.2108 | 256 | 0.6109 | 0.0069 | 35.5171 | 20.2209 |
82
+ | 0.131 | 0.2371 | 288 | 0.5748 | 0.0069 | 35.7859 | 20.6324 |
83
+ | 0.1316 | 0.2635 | 320 | 0.5705 | 0.0069 | 34.9942 | 20.1559 |
84
+ | 0.1296 | 0.2898 | 352 | 0.6122 | 0.0069 | 35.3791 | 20.0332 |
85
+ | 0.1274 | 0.3162 | 384 | 0.5848 | 0.0069 | 35.1322 | 19.8960 |
86
+ | 0.1185 | 0.3425 | 416 | 0.5458 | 0.0069 | 35.4227 | 19.8239 |
87
+ | 0.1207 | 0.3689 | 448 | 0.5714 | 0.0069 | 34.8053 | 19.6289 |
88
+ | 0.1193 | 0.3952 | 480 | 0.6553 | 0.0069 | 34.7327 | 19.3546 |
89
+ | 0.119 | 0.4216 | 512 | 0.5913 | 0.0069 | 35.0523 | 19.4629 |
90
+ | 0.122 | 0.4479 | 544 | 0.5890 | 0.0069 | 34.8489 | 19.4846 |
91
+ | 0.1203 | 0.4743 | 576 | 0.5554 | 0.0069 | 35.0886 | 19.5206 |
92
+ | 0.1164 | 0.5006 | 608 | 0.5637 | 0.0069 | 34.7690 | 19.4124 |
93
+ | 0.1173 | 0.5270 | 640 | 0.5492 | 0.0069 | 34.6601 | 19.2319 |
94
+ | 0.1175 | 0.5533 | 672 | 0.5847 | 0.0069 | 34.4785 | 19.3474 |
95
+ | 0.1154 | 0.5797 | 704 | 0.5900 | 0.0069 | 34.7618 | 18.8926 |
96
+ | 0.1136 | 0.6060 | 736 | 0.6104 | 0.0069 | 34.6092 | 19.0586 |
97
+ | 0.1142 | 0.6324 | 768 | 0.5393 | 0.0069 | 34.2533 | 18.8276 |
98
+ | 0.1156 | 0.6587 | 800 | 0.5473 | 0.0069 | 34.5221 | 18.8926 |
99
+ | 0.1125 | 0.6851 | 832 | 0.5747 | 0.0069 | 34.4858 | 18.8276 |
100
+ | 0.1107 | 0.7114 | 864 | 0.5470 | 0.0069 | 34.1880 | 18.8709 |
101
+ | 0.1088 | 0.7378 | 896 | 0.5620 | 0.0069 | 34.4785 | 18.8926 |
102
+ | 0.1111 | 0.7641 | 928 | 0.5832 | 0.0069 | 34.4059 | 18.8493 |
103
+ | 0.1081 | 0.7904 | 960 | 0.5430 | 0.0069 | 34.3623 | 18.8204 |
104
+ | 0.108 | 0.8168 | 992 | 0.5560 | 0.0069 | 34.4567 | 18.7626 |
105
+ | 0.106 | 0.8431 | 1024 | 0.5344 | 0.0069 | 34.3550 | 18.8637 |
106
+ | 0.1051 | 0.8695 | 1056 | 0.5496 | 0.0069 | 34.4567 | 18.5894 |
107
+ | 0.1096 | 0.8958 | 1088 | 0.5341 | 0.0069 | 34.1008 | 18.4811 |
108
+ | 0.1098 | 0.9222 | 1120 | 0.5339 | 0.0069 | 34.2025 | 18.4306 |
109
+ | 0.1045 | 0.9485 | 1152 | 0.5289 | 0.0069 | 34.0354 | 18.3439 |
110
+ | 0.1072 | 0.9749 | 1184 | 0.5265 | 0.0069 | 34.0863 | 18.4089 |
111
+
112
+
113
+ ### Framework versions
114
+
115
+ - Transformers 4.51.3
116
+ - Pytorch 2.5.1
117
+ - Datasets 3.6.0
118
+ - Tokenizers 0.21.1
generation_config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 4
6
+ ],
7
+ [
8
+ 2,
9
+ 11
10
+ ],
11
+ [
12
+ 3,
13
+ 3
14
+ ],
15
+ [
16
+ 3,
17
+ 6
18
+ ],
19
+ [
20
+ 3,
21
+ 11
22
+ ],
23
+ [
24
+ 3,
25
+ 14
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
+ "is_multilingual": true,
36
+ "lang_to_id": {
37
+ "<|af|>": 50327,
38
+ "<|am|>": 50334,
39
+ "<|ar|>": 50272,
40
+ "<|as|>": 50350,
41
+ "<|az|>": 50304,
42
+ "<|ba|>": 50355,
43
+ "<|be|>": 50330,
44
+ "<|bg|>": 50292,
45
+ "<|bn|>": 50302,
46
+ "<|bo|>": 50347,
47
+ "<|br|>": 50309,
48
+ "<|bs|>": 50315,
49
+ "<|ca|>": 50270,
50
+ "<|cs|>": 50283,
51
+ "<|cy|>": 50297,
52
+ "<|da|>": 50285,
53
+ "<|de|>": 50261,
54
+ "<|el|>": 50281,
55
+ "<|en|>": 50259,
56
+ "<|es|>": 50262,
57
+ "<|et|>": 50307,
58
+ "<|eu|>": 50310,
59
+ "<|fa|>": 50300,
60
+ "<|fi|>": 50277,
61
+ "<|fo|>": 50338,
62
+ "<|fr|>": 50265,
63
+ "<|gl|>": 50319,
64
+ "<|gu|>": 50333,
65
+ "<|haw|>": 50352,
66
+ "<|ha|>": 50354,
67
+ "<|he|>": 50279,
68
+ "<|hi|>": 50276,
69
+ "<|hr|>": 50291,
70
+ "<|ht|>": 50339,
71
+ "<|hu|>": 50286,
72
+ "<|hy|>": 50312,
73
+ "<|id|>": 50275,
74
+ "<|is|>": 50311,
75
+ "<|it|>": 50274,
76
+ "<|ja|>": 50266,
77
+ "<|jw|>": 50356,
78
+ "<|ka|>": 50329,
79
+ "<|kk|>": 50316,
80
+ "<|km|>": 50323,
81
+ "<|kn|>": 50306,
82
+ "<|ko|>": 50264,
83
+ "<|la|>": 50294,
84
+ "<|lb|>": 50345,
85
+ "<|ln|>": 50353,
86
+ "<|lo|>": 50336,
87
+ "<|lt|>": 50293,
88
+ "<|lv|>": 50301,
89
+ "<|mg|>": 50349,
90
+ "<|mi|>": 50295,
91
+ "<|mk|>": 50308,
92
+ "<|ml|>": 50296,
93
+ "<|mn|>": 50314,
94
+ "<|mr|>": 50320,
95
+ "<|ms|>": 50282,
96
+ "<|mt|>": 50343,
97
+ "<|my|>": 50346,
98
+ "<|ne|>": 50313,
99
+ "<|nl|>": 50271,
100
+ "<|nn|>": 50342,
101
+ "<|no|>": 50288,
102
+ "<|oc|>": 50328,
103
+ "<|pa|>": 50321,
104
+ "<|pl|>": 50269,
105
+ "<|ps|>": 50340,
106
+ "<|pt|>": 50267,
107
+ "<|ro|>": 50284,
108
+ "<|ru|>": 50263,
109
+ "<|sa|>": 50344,
110
+ "<|sd|>": 50332,
111
+ "<|si|>": 50322,
112
+ "<|sk|>": 50298,
113
+ "<|sl|>": 50305,
114
+ "<|sn|>": 50324,
115
+ "<|so|>": 50326,
116
+ "<|sq|>": 50317,
117
+ "<|sr|>": 50303,
118
+ "<|su|>": 50357,
119
+ "<|sv|>": 50273,
120
+ "<|sw|>": 50318,
121
+ "<|ta|>": 50287,
122
+ "<|te|>": 50299,
123
+ "<|tg|>": 50331,
124
+ "<|th|>": 50289,
125
+ "<|tk|>": 50341,
126
+ "<|tl|>": 50348,
127
+ "<|tr|>": 50268,
128
+ "<|tt|>": 50351,
129
+ "<|uk|>": 50280,
130
+ "<|ur|>": 50290,
131
+ "<|uz|>": 50337,
132
+ "<|vi|>": 50278,
133
+ "<|yi|>": 50335,
134
+ "<|yo|>": 50325,
135
+ "<|yue|>": 50358,
136
+ "<|zh|>": 50260
137
+ },
138
+ "language": "serbian",
139
+ "max_initial_timestamp_index": 50,
140
+ "max_length": 448,
141
+ "no_timestamps_token_id": 50364,
142
+ "pad_token_id": 50257,
143
+ "prev_sot_token_id": 50362,
144
+ "return_timestamps": false,
145
+ "suppress_tokens": [
146
+ 1,
147
+ 2,
148
+ 7,
149
+ 8,
150
+ 9,
151
+ 10,
152
+ 14,
153
+ 25,
154
+ 26,
155
+ 27,
156
+ 28,
157
+ 29,
158
+ 31,
159
+ 58,
160
+ 59,
161
+ 60,
162
+ 61,
163
+ 62,
164
+ 63,
165
+ 90,
166
+ 91,
167
+ 92,
168
+ 93,
169
+ 359,
170
+ 503,
171
+ 522,
172
+ 542,
173
+ 873,
174
+ 893,
175
+ 902,
176
+ 918,
177
+ 922,
178
+ 931,
179
+ 1350,
180
+ 1853,
181
+ 1982,
182
+ 2460,
183
+ 2627,
184
+ 3246,
185
+ 3253,
186
+ 3268,
187
+ 3536,
188
+ 3846,
189
+ 3961,
190
+ 4183,
191
+ 4667,
192
+ 6585,
193
+ 6647,
194
+ 7273,
195
+ 9061,
196
+ 9383,
197
+ 10428,
198
+ 10929,
199
+ 11938,
200
+ 12033,
201
+ 12331,
202
+ 12562,
203
+ 13793,
204
+ 14157,
205
+ 14635,
206
+ 15265,
207
+ 15618,
208
+ 16553,
209
+ 16604,
210
+ 18362,
211
+ 18956,
212
+ 20075,
213
+ 21675,
214
+ 22520,
215
+ 26130,
216
+ 26161,
217
+ 26435,
218
+ 28279,
219
+ 29464,
220
+ 31650,
221
+ 32302,
222
+ 32470,
223
+ 36865,
224
+ 42863,
225
+ 47425,
226
+ 49870,
227
+ 50254,
228
+ 50258,
229
+ 50359,
230
+ 50360,
231
+ 50361,
232
+ 50362,
233
+ 50363
234
+ ],
235
+ "task": "transcribe",
236
+ "task_to_id": {
237
+ "transcribe": 50360,
238
+ "translate": 50359
239
+ },
240
+ "transformers_version": "4.51.3"
241
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e479e6c66d0ad960fbc03be3aba192459b50d14475971923e1b8eddec1558f2
3
  size 3235581408
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ae0803d52fcff4ba0950cddb8cc790319379cd7f3018ea2564666e327fd416
3
  size 3235581408
runs/May22_01-19-50_tikgpu08/events.out.tfevents.1747869983.tikgpu08.375926.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:835953f931239401f78cfb7421d4f9dcba396094cae3c674c083ec9ad2fb14cc
3
- size 47775
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65319ca5bae991b9578ec1717577bbeca9acd5e65f34b73f46dabeac49a0633e
3
+ size 48129
runs/May22_01-19-50_tikgpu08/events.out.tfevents.1747949939.tikgpu08.375926.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a70179ad88ba8e1f51f0171cd04a258dfbf48872d3b5e519264011ee9c573cd
3
+ size 525