Dearlie commited on
Commit
0ea9b57
1 Parent(s): 877cde8

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-base
6
+ tags:
7
+ - generated_from_trainer
8
+ datasets:
9
+ - AIHub/noise
10
+ model-index:
11
+ - name: Whisper Base Noise Ko - Dearlie
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # Whisper Base Noise Ko - Dearlie
19
+
20
+ This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Noise Data dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 1.3670
23
+ - Cer: 57.4924
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 1e-05
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 500
49
+ - training_steps: 4000
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
55
+ |:-------------:|:------:|:----:|:---------------:|:-------:|
56
+ | 1.6034 | 0.8780 | 1000 | 1.6217 | 75.3884 |
57
+ | 1.4053 | 1.7559 | 2000 | 1.4598 | 60.7893 |
58
+ | 1.2681 | 2.6339 | 3000 | 1.3881 | 61.1636 |
59
+ | 1.1608 | 3.5119 | 4000 | 1.3670 | 57.4924 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.41.0.dev0
65
+ - Pytorch 2.3.0+cu121
66
+ - Datasets 2.19.0
67
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 3,
5
+ 1
6
+ ],
7
+ [
8
+ 4,
9
+ 2
10
+ ],
11
+ [
12
+ 4,
13
+ 3
14
+ ],
15
+ [
16
+ 4,
17
+ 7
18
+ ],
19
+ [
20
+ 5,
21
+ 1
22
+ ],
23
+ [
24
+ 5,
25
+ 2
26
+ ],
27
+ [
28
+ 5,
29
+ 4
30
+ ],
31
+ [
32
+ 5,
33
+ 6
34
+ ]
35
+ ],
36
+ "begin_suppress_tokens": [
37
+ 220,
38
+ 50257
39
+ ],
40
+ "bos_token_id": 50257,
41
+ "decoder_start_token_id": 50258,
42
+ "eos_token_id": 50257,
43
+ "is_multilingual": true,
44
+ "lang_to_id": {
45
+ "<|af|>": 50327,
46
+ "<|am|>": 50334,
47
+ "<|ar|>": 50272,
48
+ "<|as|>": 50350,
49
+ "<|az|>": 50304,
50
+ "<|ba|>": 50355,
51
+ "<|be|>": 50330,
52
+ "<|bg|>": 50292,
53
+ "<|bn|>": 50302,
54
+ "<|bo|>": 50347,
55
+ "<|br|>": 50309,
56
+ "<|bs|>": 50315,
57
+ "<|ca|>": 50270,
58
+ "<|cs|>": 50283,
59
+ "<|cy|>": 50297,
60
+ "<|da|>": 50285,
61
+ "<|de|>": 50261,
62
+ "<|el|>": 50281,
63
+ "<|en|>": 50259,
64
+ "<|es|>": 50262,
65
+ "<|et|>": 50307,
66
+ "<|eu|>": 50310,
67
+ "<|fa|>": 50300,
68
+ "<|fi|>": 50277,
69
+ "<|fo|>": 50338,
70
+ "<|fr|>": 50265,
71
+ "<|gl|>": 50319,
72
+ "<|gu|>": 50333,
73
+ "<|haw|>": 50352,
74
+ "<|ha|>": 50354,
75
+ "<|he|>": 50279,
76
+ "<|hi|>": 50276,
77
+ "<|hr|>": 50291,
78
+ "<|ht|>": 50339,
79
+ "<|hu|>": 50286,
80
+ "<|hy|>": 50312,
81
+ "<|id|>": 50275,
82
+ "<|is|>": 50311,
83
+ "<|it|>": 50274,
84
+ "<|ja|>": 50266,
85
+ "<|jw|>": 50356,
86
+ "<|ka|>": 50329,
87
+ "<|kk|>": 50316,
88
+ "<|km|>": 50323,
89
+ "<|kn|>": 50306,
90
+ "<|ko|>": 50264,
91
+ "<|la|>": 50294,
92
+ "<|lb|>": 50345,
93
+ "<|ln|>": 50353,
94
+ "<|lo|>": 50336,
95
+ "<|lt|>": 50293,
96
+ "<|lv|>": 50301,
97
+ "<|mg|>": 50349,
98
+ "<|mi|>": 50295,
99
+ "<|mk|>": 50308,
100
+ "<|ml|>": 50296,
101
+ "<|mn|>": 50314,
102
+ "<|mr|>": 50320,
103
+ "<|ms|>": 50282,
104
+ "<|mt|>": 50343,
105
+ "<|my|>": 50346,
106
+ "<|ne|>": 50313,
107
+ "<|nl|>": 50271,
108
+ "<|nn|>": 50342,
109
+ "<|no|>": 50288,
110
+ "<|oc|>": 50328,
111
+ "<|pa|>": 50321,
112
+ "<|pl|>": 50269,
113
+ "<|ps|>": 50340,
114
+ "<|pt|>": 50267,
115
+ "<|ro|>": 50284,
116
+ "<|ru|>": 50263,
117
+ "<|sa|>": 50344,
118
+ "<|sd|>": 50332,
119
+ "<|si|>": 50322,
120
+ "<|sk|>": 50298,
121
+ "<|sl|>": 50305,
122
+ "<|sn|>": 50324,
123
+ "<|so|>": 50326,
124
+ "<|sq|>": 50317,
125
+ "<|sr|>": 50303,
126
+ "<|su|>": 50357,
127
+ "<|sv|>": 50273,
128
+ "<|sw|>": 50318,
129
+ "<|ta|>": 50287,
130
+ "<|te|>": 50299,
131
+ "<|tg|>": 50331,
132
+ "<|th|>": 50289,
133
+ "<|tk|>": 50341,
134
+ "<|tl|>": 50348,
135
+ "<|tr|>": 50268,
136
+ "<|tt|>": 50351,
137
+ "<|uk|>": 50280,
138
+ "<|ur|>": 50290,
139
+ "<|uz|>": 50337,
140
+ "<|vi|>": 50278,
141
+ "<|yi|>": 50335,
142
+ "<|yo|>": 50325,
143
+ "<|zh|>": 50260
144
+ },
145
+ "language": "korean",
146
+ "max_initial_timestamp_index": 50,
147
+ "max_length": 448,
148
+ "no_timestamps_token_id": 50363,
149
+ "pad_token_id": 50257,
150
+ "prev_sot_token_id": 50361,
151
+ "return_timestamps": false,
152
+ "suppress_tokens": [
153
+ 1,
154
+ 2,
155
+ 7,
156
+ 8,
157
+ 9,
158
+ 10,
159
+ 14,
160
+ 25,
161
+ 26,
162
+ 27,
163
+ 28,
164
+ 29,
165
+ 31,
166
+ 58,
167
+ 59,
168
+ 60,
169
+ 61,
170
+ 62,
171
+ 63,
172
+ 90,
173
+ 91,
174
+ 92,
175
+ 93,
176
+ 359,
177
+ 503,
178
+ 522,
179
+ 542,
180
+ 873,
181
+ 893,
182
+ 902,
183
+ 918,
184
+ 922,
185
+ 931,
186
+ 1350,
187
+ 1853,
188
+ 1982,
189
+ 2460,
190
+ 2627,
191
+ 3246,
192
+ 3253,
193
+ 3268,
194
+ 3536,
195
+ 3846,
196
+ 3961,
197
+ 4183,
198
+ 4667,
199
+ 6585,
200
+ 6647,
201
+ 7273,
202
+ 9061,
203
+ 9383,
204
+ 10428,
205
+ 10929,
206
+ 11938,
207
+ 12033,
208
+ 12331,
209
+ 12562,
210
+ 13793,
211
+ 14157,
212
+ 14635,
213
+ 15265,
214
+ 15618,
215
+ 16553,
216
+ 16604,
217
+ 18362,
218
+ 18956,
219
+ 20075,
220
+ 21675,
221
+ 22520,
222
+ 26130,
223
+ 26161,
224
+ 26435,
225
+ 28279,
226
+ 29464,
227
+ 31650,
228
+ 32302,
229
+ 32470,
230
+ 36865,
231
+ 42863,
232
+ 47425,
233
+ 49870,
234
+ 50254,
235
+ 50258,
236
+ 50358,
237
+ 50359,
238
+ 50360,
239
+ 50361,
240
+ 50362
241
+ ],
242
+ "task": "transcribe",
243
+ "task_to_id": {
244
+ "transcribe": 50359,
245
+ "translate": 50358
246
+ },
247
+ "transformers_version": "4.41.0.dev0"
248
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8976e78d72d0997e22580d05e549d9876016f0b1958a07b48a5435fb916b6a9
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:507ab437fa6921e5e4d991f57e70e3db2071fd79e3105ee33dbb9a975506f0d7
3
  size 290403936
runs/May03_21-25-38_Dearlie/events.out.tfevents.1714739140.Dearlie.24376.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e80e992bb1603f2da90fb4cc08aabf37b68b73b741a490e9b47a8d0ab7978e0
3
- size 31852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f817b18cbde22fbc8885e6cc8e80c528ec45e2b7de8fdc6178708e951d56434
3
+ size 40964