freshpearYoon commited on
Commit
0306ed9
·
verified ·
1 Parent(s): 97f6f37

End of training

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ license: apache-2.0
5
+ base_model: openai/whisper-large-v3
6
+ tags:
7
+ - hf-asr-leaderboard
8
+ - generated_from_trainer
9
+ metrics:
10
+ - wer
11
+ model-index:
12
+ - name: whisper_finetune
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_finetune
20
+
21
+ This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the aihub_100000 dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.0532
24
+ - Cer: 6.2644
25
+ - Wer: 23.9434
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 1e-08
45
+ - train_batch_size: 16
46
+ - eval_batch_size: 16
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - lr_scheduler_warmup_steps: 500
51
+ - training_steps: 2000
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
57
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
58
+ | 1.5045 | 0.16 | 1000 | 1.4103 | 6.8826 | 26.6172 |
59
+ | 1.0745 | 0.32 | 2000 | 1.0532 | 6.2644 | 23.9434 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.38.0.dev0
65
+ - Pytorch 1.14.0a0+410ce96
66
+ - Datasets 2.17.0
67
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,269 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 50264
55
+ ],
56
+ [
57
+ 2,
58
+ 50360
59
+ ],
60
+ [
61
+ 3,
62
+ 50364
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
+ "<|yue|>": 50358,
166
+ "<|zh|>": 50260
167
+ },
168
+ "max_initial_timestamp_index": 50,
169
+ "max_length": 448,
170
+ "no_timestamps_token_id": 50364,
171
+ "pad_token_id": 50257,
172
+ "prev_sot_token_id": 50362,
173
+ "return_timestamps": false,
174
+ "suppress_tokens": [
175
+ 1,
176
+ 2,
177
+ 7,
178
+ 8,
179
+ 9,
180
+ 10,
181
+ 14,
182
+ 25,
183
+ 26,
184
+ 27,
185
+ 28,
186
+ 29,
187
+ 31,
188
+ 58,
189
+ 59,
190
+ 60,
191
+ 61,
192
+ 62,
193
+ 63,
194
+ 90,
195
+ 91,
196
+ 92,
197
+ 93,
198
+ 359,
199
+ 503,
200
+ 522,
201
+ 542,
202
+ 873,
203
+ 893,
204
+ 902,
205
+ 918,
206
+ 922,
207
+ 931,
208
+ 1350,
209
+ 1853,
210
+ 1982,
211
+ 2460,
212
+ 2627,
213
+ 3246,
214
+ 3253,
215
+ 3268,
216
+ 3536,
217
+ 3846,
218
+ 3961,
219
+ 4183,
220
+ 4667,
221
+ 6585,
222
+ 6647,
223
+ 7273,
224
+ 9061,
225
+ 9383,
226
+ 10428,
227
+ 10929,
228
+ 11938,
229
+ 12033,
230
+ 12331,
231
+ 12562,
232
+ 13793,
233
+ 14157,
234
+ 14635,
235
+ 15265,
236
+ 15618,
237
+ 16553,
238
+ 16604,
239
+ 18362,
240
+ 18956,
241
+ 20075,
242
+ 21675,
243
+ 22520,
244
+ 26130,
245
+ 26161,
246
+ 26435,
247
+ 28279,
248
+ 29464,
249
+ 31650,
250
+ 32302,
251
+ 32470,
252
+ 36865,
253
+ 42863,
254
+ 47425,
255
+ 49870,
256
+ 50254,
257
+ 50258,
258
+ 50359,
259
+ 50360,
260
+ 50361,
261
+ 50362,
262
+ 50363
263
+ ],
264
+ "task_to_id": {
265
+ "transcribe": 50360,
266
+ "translate": 50359
267
+ },
268
+ "transformers_version": "4.38.0.dev0"
269
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c1179026d2e8cc32fc98a3d1cd5c2e42f7beabc5e8f40af10cd6ea782a84b8
3
+ size 4993448880
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8db9513966885658d9c7fd1efd93e05dbcc6e06a35894c3e28c86291dad6d706
3
+ size 1180663192
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb19_07-05-51_main1/events.out.tfevents.1708326351.main1.29409.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93ffba85d222a8e5b615a2afbb5ef44470205b481c0b175759972377fc23998f
3
- size 18683
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5003d6fbda3b7e6d0beb67697e856aa66cbded22c985c72078528382678ad312
3
+ size 19037