freshpearYoon commited on
Commit
5268d98
1 Parent(s): 2e8cb50

End of training

Browse files
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ko
4
+ license: apache-2.0
5
+ base_model: openai/whisper-large-v2
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-v2](https://huggingface.co/openai/whisper-large-v2) on the aihub_100000 dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.1966
24
+ - Cer: 5.9236
25
+ - Wer: 23.0770
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-06
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: 4000
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
57
+ |:-------------:|:-----:|:----:|:------:|:---------------:|:-------:|
58
+ | 0.1866 | 0.16 | 1000 | 6.0386 | 0.1963 | 23.2684 |
59
+ | 0.1788 | 0.32 | 2000 | 6.0483 | 0.1979 | 23.2267 |
60
+ | 0.1541 | 0.48 | 3000 | 6.0116 | 0.1929 | 23.5519 |
61
+ | 0.1692 | 0.64 | 4000 | 0.1966 | 5.9236 | 23.0770 |
62
+
63
+
64
+ ### Framework versions
65
+
66
+ - Transformers 4.38.0.dev0
67
+ - Pytorch 1.14.0a0+410ce96
68
+ - Datasets 2.16.1
69
+ - Tokenizers 0.15.1
generation_config.json ADDED
@@ -0,0 +1,231 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 10,
5
+ 12
6
+ ],
7
+ [
8
+ 13,
9
+ 17
10
+ ],
11
+ [
12
+ 16,
13
+ 11
14
+ ],
15
+ [
16
+ 16,
17
+ 12
18
+ ],
19
+ [
20
+ 16,
21
+ 13
22
+ ],
23
+ [
24
+ 17,
25
+ 15
26
+ ],
27
+ [
28
+ 17,
29
+ 16
30
+ ],
31
+ [
32
+ 18,
33
+ 4
34
+ ],
35
+ [
36
+ 18,
37
+ 11
38
+ ],
39
+ [
40
+ 18,
41
+ 19
42
+ ],
43
+ [
44
+ 19,
45
+ 11
46
+ ],
47
+ [
48
+ 21,
49
+ 2
50
+ ],
51
+ [
52
+ 21,
53
+ 3
54
+ ],
55
+ [
56
+ 22,
57
+ 3
58
+ ],
59
+ [
60
+ 22,
61
+ 9
62
+ ],
63
+ [
64
+ 22,
65
+ 12
66
+ ],
67
+ [
68
+ 23,
69
+ 5
70
+ ],
71
+ [
72
+ 23,
73
+ 7
74
+ ],
75
+ [
76
+ 23,
77
+ 13
78
+ ],
79
+ [
80
+ 25,
81
+ 5
82
+ ],
83
+ [
84
+ 26,
85
+ 1
86
+ ],
87
+ [
88
+ 26,
89
+ 12
90
+ ],
91
+ [
92
+ 27,
93
+ 15
94
+ ]
95
+ ],
96
+ "begin_suppress_tokens": [
97
+ 220,
98
+ 50257
99
+ ],
100
+ "bos_token_id": 50257,
101
+ "decoder_start_token_id": 50258,
102
+ "eos_token_id": 50257,
103
+ "forced_decoder_ids": [
104
+ [
105
+ 1,
106
+ 50264
107
+ ],
108
+ [
109
+ 2,
110
+ 50359
111
+ ],
112
+ [
113
+ 3,
114
+ 50363
115
+ ]
116
+ ],
117
+ "is_multilingual": true,
118
+ "lang_to_id": {
119
+ "<|af|>": 50327,
120
+ "<|am|>": 50334,
121
+ "<|ar|>": 50272,
122
+ "<|as|>": 50350,
123
+ "<|az|>": 50304,
124
+ "<|ba|>": 50355,
125
+ "<|be|>": 50330,
126
+ "<|bg|>": 50292,
127
+ "<|bn|>": 50302,
128
+ "<|bo|>": 50347,
129
+ "<|br|>": 50309,
130
+ "<|bs|>": 50315,
131
+ "<|ca|>": 50270,
132
+ "<|cs|>": 50283,
133
+ "<|cy|>": 50297,
134
+ "<|da|>": 50285,
135
+ "<|de|>": 50261,
136
+ "<|el|>": 50281,
137
+ "<|en|>": 50259,
138
+ "<|es|>": 50262,
139
+ "<|et|>": 50307,
140
+ "<|eu|>": 50310,
141
+ "<|fa|>": 50300,
142
+ "<|fi|>": 50277,
143
+ "<|fo|>": 50338,
144
+ "<|fr|>": 50265,
145
+ "<|gl|>": 50319,
146
+ "<|gu|>": 50333,
147
+ "<|haw|>": 50352,
148
+ "<|ha|>": 50354,
149
+ "<|he|>": 50279,
150
+ "<|hi|>": 50276,
151
+ "<|hr|>": 50291,
152
+ "<|ht|>": 50339,
153
+ "<|hu|>": 50286,
154
+ "<|hy|>": 50312,
155
+ "<|id|>": 50275,
156
+ "<|is|>": 50311,
157
+ "<|it|>": 50274,
158
+ "<|ja|>": 50266,
159
+ "<|jw|>": 50356,
160
+ "<|ka|>": 50329,
161
+ "<|kk|>": 50316,
162
+ "<|km|>": 50323,
163
+ "<|kn|>": 50306,
164
+ "<|ko|>": 50264,
165
+ "<|la|>": 50294,
166
+ "<|lb|>": 50345,
167
+ "<|ln|>": 50353,
168
+ "<|lo|>": 50336,
169
+ "<|lt|>": 50293,
170
+ "<|lv|>": 50301,
171
+ "<|mg|>": 50349,
172
+ "<|mi|>": 50295,
173
+ "<|mk|>": 50308,
174
+ "<|ml|>": 50296,
175
+ "<|mn|>": 50314,
176
+ "<|mr|>": 50320,
177
+ "<|ms|>": 50282,
178
+ "<|mt|>": 50343,
179
+ "<|my|>": 50346,
180
+ "<|ne|>": 50313,
181
+ "<|nl|>": 50271,
182
+ "<|nn|>": 50342,
183
+ "<|no|>": 50288,
184
+ "<|oc|>": 50328,
185
+ "<|pa|>": 50321,
186
+ "<|pl|>": 50269,
187
+ "<|ps|>": 50340,
188
+ "<|pt|>": 50267,
189
+ "<|ro|>": 50284,
190
+ "<|ru|>": 50263,
191
+ "<|sa|>": 50344,
192
+ "<|sd|>": 50332,
193
+ "<|si|>": 50322,
194
+ "<|sk|>": 50298,
195
+ "<|sl|>": 50305,
196
+ "<|sn|>": 50324,
197
+ "<|so|>": 50326,
198
+ "<|sq|>": 50317,
199
+ "<|sr|>": 50303,
200
+ "<|su|>": 50357,
201
+ "<|sv|>": 50273,
202
+ "<|sw|>": 50318,
203
+ "<|ta|>": 50287,
204
+ "<|te|>": 50299,
205
+ "<|tg|>": 50331,
206
+ "<|th|>": 50289,
207
+ "<|tk|>": 50341,
208
+ "<|tl|>": 50348,
209
+ "<|tr|>": 50268,
210
+ "<|tt|>": 50351,
211
+ "<|uk|>": 50280,
212
+ "<|ur|>": 50290,
213
+ "<|uz|>": 50337,
214
+ "<|vi|>": 50278,
215
+ "<|yi|>": 50335,
216
+ "<|yo|>": 50325,
217
+ "<|zh|>": 50260
218
+ },
219
+ "max_initial_timestamp_index": 50,
220
+ "max_length": 448,
221
+ "no_timestamps_token_id": 50363,
222
+ "pad_token_id": 50257,
223
+ "prev_sot_token_id": 50361,
224
+ "return_timestamps": false,
225
+ "suppress_tokens": [],
226
+ "task_to_id": {
227
+ "transcribe": 50359,
228
+ "translate": 50358
229
+ },
230
+ "transformers_version": "4.38.0.dev0"
231
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fa096c3bc413dbff9d40f5e128397c362060b98621f681e9a8ca74eb3e2b2a8
3
+ size 4992706480
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447f84647618948b46f4979416a26eef3e4632a128c72c3ae7bc78111ce943cc
3
+ size 1180663192
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb05_11-55-51_main1/events.out.tfevents.1707134213.main1.262.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4010b12c1c2e31dd1a15c9df683bf766af6a829ab47474b4a7a2332ea2b429ac
3
- size 11935
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e303c3615c7f5bc96d398f9c22be18a50a9c478d0195add8a79d9e0d6c306fd
3
+ size 12289