linl03 commited on
Commit
bc39e11
1 Parent(s): 36fab0b

End of training

Browse files
README.md CHANGED
@@ -1,59 +1,56 @@
1
- ---
2
- library_name: transformers
3
- language:
4
- - vi
5
- license: apache-2.0
6
- base_model: openai/whisper-small
7
- tags:
8
- - generated_from_trainer
9
- datasets:
10
- - mozilla-foundation/common_voice_11_0
11
- model-index:
12
- - name: Whisper small vi - Ox
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 small vi - Ox
20
-
21
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
22
-
23
- ## Model description
24
-
25
- More information needed
26
-
27
- ## Intended uses & limitations
28
-
29
- More information needed
30
-
31
- ## Training and evaluation data
32
-
33
- More information needed
34
-
35
- ## Training procedure
36
-
37
- ### Training hyperparameters
38
-
39
- The following hyperparameters were used during training:
40
- - learning_rate: 1e-05
41
- - train_batch_size: 16
42
- - eval_batch_size: 8
43
- - seed: 42
44
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
- - lr_scheduler_type: linear
46
- - lr_scheduler_warmup_steps: 500
47
- - num_epochs: 3.0
48
- - mixed_precision_training: Native AMP
49
-
50
- ### Training results
51
-
52
-
53
-
54
- ### Framework versions
55
-
56
- - Transformers 4.46.1
57
- - Pytorch 2.5.0+cu121
58
- - Datasets 3.1.0
59
- - Tokenizers 0.20.1
 
1
+ ---
2
+ language:
3
+ - vi
4
+ license: apache-2.0
5
+ base_model: openai/whisper-small
6
+ tags:
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: Whisper small vi - Ox
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # Whisper small vi - Ox
17
+
18
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 1e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 500
44
+ - num_epochs: 3.0
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - Transformers 4.39.3
54
+ - Pytorch 2.4.1
55
+ - Datasets 3.0.1
56
+ - Tokenizers 0.15.2
 
 
 
generation_config.json CHANGED
@@ -1,254 +1,256 @@
1
- {
2
- "alignment_heads": [
3
- [
4
- 5,
5
- 3
6
- ],
7
- [
8
- 5,
9
- 9
10
- ],
11
- [
12
- 8,
13
- 0
14
- ],
15
- [
16
- 8,
17
- 4
18
- ],
19
- [
20
- 8,
21
- 7
22
- ],
23
- [
24
- 8,
25
- 8
26
- ],
27
- [
28
- 9,
29
- 0
30
- ],
31
- [
32
- 9,
33
- 7
34
- ],
35
- [
36
- 9,
37
- 9
38
- ],
39
- [
40
- 10,
41
- 5
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
- "is_multilingual": true,
52
- "lang_to_id": {
53
- "<|af|>": 50327,
54
- "<|am|>": 50334,
55
- "<|ar|>": 50272,
56
- "<|as|>": 50350,
57
- "<|az|>": 50304,
58
- "<|ba|>": 50355,
59
- "<|be|>": 50330,
60
- "<|bg|>": 50292,
61
- "<|bn|>": 50302,
62
- "<|bo|>": 50347,
63
- "<|br|>": 50309,
64
- "<|bs|>": 50315,
65
- "<|ca|>": 50270,
66
- "<|cs|>": 50283,
67
- "<|cy|>": 50297,
68
- "<|da|>": 50285,
69
- "<|de|>": 50261,
70
- "<|el|>": 50281,
71
- "<|en|>": 50259,
72
- "<|es|>": 50262,
73
- "<|et|>": 50307,
74
- "<|eu|>": 50310,
75
- "<|fa|>": 50300,
76
- "<|fi|>": 50277,
77
- "<|fo|>": 50338,
78
- "<|fr|>": 50265,
79
- "<|gl|>": 50319,
80
- "<|gu|>": 50333,
81
- "<|haw|>": 50352,
82
- "<|ha|>": 50354,
83
- "<|he|>": 50279,
84
- "<|hi|>": 50276,
85
- "<|hr|>": 50291,
86
- "<|ht|>": 50339,
87
- "<|hu|>": 50286,
88
- "<|hy|>": 50312,
89
- "<|id|>": 50275,
90
- "<|is|>": 50311,
91
- "<|it|>": 50274,
92
- "<|ja|>": 50266,
93
- "<|jw|>": 50356,
94
- "<|ka|>": 50329,
95
- "<|kk|>": 50316,
96
- "<|km|>": 50323,
97
- "<|kn|>": 50306,
98
- "<|ko|>": 50264,
99
- "<|la|>": 50294,
100
- "<|lb|>": 50345,
101
- "<|ln|>": 50353,
102
- "<|lo|>": 50336,
103
- "<|lt|>": 50293,
104
- "<|lv|>": 50301,
105
- "<|mg|>": 50349,
106
- "<|mi|>": 50295,
107
- "<|mk|>": 50308,
108
- "<|ml|>": 50296,
109
- "<|mn|>": 50314,
110
- "<|mr|>": 50320,
111
- "<|ms|>": 50282,
112
- "<|mt|>": 50343,
113
- "<|my|>": 50346,
114
- "<|ne|>": 50313,
115
- "<|nl|>": 50271,
116
- "<|nn|>": 50342,
117
- "<|no|>": 50288,
118
- "<|oc|>": 50328,
119
- "<|pa|>": 50321,
120
- "<|pl|>": 50269,
121
- "<|ps|>": 50340,
122
- "<|pt|>": 50267,
123
- "<|ro|>": 50284,
124
- "<|ru|>": 50263,
125
- "<|sa|>": 50344,
126
- "<|sd|>": 50332,
127
- "<|si|>": 50322,
128
- "<|sk|>": 50298,
129
- "<|sl|>": 50305,
130
- "<|sn|>": 50324,
131
- "<|so|>": 50326,
132
- "<|sq|>": 50317,
133
- "<|sr|>": 50303,
134
- "<|su|>": 50357,
135
- "<|sv|>": 50273,
136
- "<|sw|>": 50318,
137
- "<|ta|>": 50287,
138
- "<|te|>": 50299,
139
- "<|tg|>": 50331,
140
- "<|th|>": 50289,
141
- "<|tk|>": 50341,
142
- "<|tl|>": 50348,
143
- "<|tr|>": 50268,
144
- "<|tt|>": 50351,
145
- "<|uk|>": 50280,
146
- "<|ur|>": 50290,
147
- "<|uz|>": 50337,
148
- "<|vi|>": 50278,
149
- "<|yi|>": 50335,
150
- "<|yo|>": 50325,
151
- "<|zh|>": 50260
152
- },
153
- "language": "vi",
154
- "max_initial_timestamp_index": 50,
155
- "max_length": 448,
156
- "no_timestamps_token_id": 50363,
157
- "pad_token_id": 50257,
158
- "prev_sot_token_id": 50361,
159
- "return_timestamps": false,
160
- "suppress_tokens": [
161
- 1,
162
- 2,
163
- 7,
164
- 8,
165
- 9,
166
- 10,
167
- 14,
168
- 25,
169
- 26,
170
- 27,
171
- 28,
172
- 29,
173
- 31,
174
- 58,
175
- 59,
176
- 60,
177
- 61,
178
- 62,
179
- 63,
180
- 90,
181
- 91,
182
- 92,
183
- 93,
184
- 359,
185
- 503,
186
- 522,
187
- 542,
188
- 873,
189
- 893,
190
- 902,
191
- 918,
192
- 922,
193
- 931,
194
- 1350,
195
- 1853,
196
- 1982,
197
- 2460,
198
- 2627,
199
- 3246,
200
- 3253,
201
- 3268,
202
- 3536,
203
- 3846,
204
- 3961,
205
- 4183,
206
- 4667,
207
- 6585,
208
- 6647,
209
- 7273,
210
- 9061,
211
- 9383,
212
- 10428,
213
- 10929,
214
- 11938,
215
- 12033,
216
- 12331,
217
- 12562,
218
- 13793,
219
- 14157,
220
- 14635,
221
- 15265,
222
- 15618,
223
- 16553,
224
- 16604,
225
- 18362,
226
- 18956,
227
- 20075,
228
- 21675,
229
- 22520,
230
- 26130,
231
- 26161,
232
- 26435,
233
- 28279,
234
- 29464,
235
- 31650,
236
- 32302,
237
- 32470,
238
- 36865,
239
- 42863,
240
- 47425,
241
- 49870,
242
- 50254,
243
- 50258,
244
- 50360,
245
- 50361,
246
- 50362
247
- ],
248
- "task": "transcribe",
249
- "task_to_id": {
250
- "transcribe": 50359,
251
- "translate": 50358
252
- },
253
- "transformers_version": "4.46.1"
254
- }
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 5,
5
+ 3
6
+ ],
7
+ [
8
+ 5,
9
+ 9
10
+ ],
11
+ [
12
+ 8,
13
+ 0
14
+ ],
15
+ [
16
+ 8,
17
+ 4
18
+ ],
19
+ [
20
+ 8,
21
+ 7
22
+ ],
23
+ [
24
+ 8,
25
+ 8
26
+ ],
27
+ [
28
+ 9,
29
+ 0
30
+ ],
31
+ [
32
+ 9,
33
+ 7
34
+ ],
35
+ [
36
+ 9,
37
+ 9
38
+ ],
39
+ [
40
+ 10,
41
+ 5
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
+ "is_multilingual": true,
52
+ "lang_to_id": {
53
+ "<|af|>": 50327,
54
+ "<|am|>": 50334,
55
+ "<|ar|>": 50272,
56
+ "<|as|>": 50350,
57
+ "<|az|>": 50304,
58
+ "<|ba|>": 50355,
59
+ "<|be|>": 50330,
60
+ "<|bg|>": 50292,
61
+ "<|bn|>": 50302,
62
+ "<|bo|>": 50347,
63
+ "<|br|>": 50309,
64
+ "<|bs|>": 50315,
65
+ "<|ca|>": 50270,
66
+ "<|cs|>": 50283,
67
+ "<|cy|>": 50297,
68
+ "<|da|>": 50285,
69
+ "<|de|>": 50261,
70
+ "<|el|>": 50281,
71
+ "<|en|>": 50259,
72
+ "<|es|>": 50262,
73
+ "<|et|>": 50307,
74
+ "<|eu|>": 50310,
75
+ "<|fa|>": 50300,
76
+ "<|fi|>": 50277,
77
+ "<|fo|>": 50338,
78
+ "<|fr|>": 50265,
79
+ "<|gl|>": 50319,
80
+ "<|gu|>": 50333,
81
+ "<|haw|>": 50352,
82
+ "<|ha|>": 50354,
83
+ "<|he|>": 50279,
84
+ "<|hi|>": 50276,
85
+ "<|hr|>": 50291,
86
+ "<|ht|>": 50339,
87
+ "<|hu|>": 50286,
88
+ "<|hy|>": 50312,
89
+ "<|id|>": 50275,
90
+ "<|is|>": 50311,
91
+ "<|it|>": 50274,
92
+ "<|ja|>": 50266,
93
+ "<|jw|>": 50356,
94
+ "<|ka|>": 50329,
95
+ "<|kk|>": 50316,
96
+ "<|km|>": 50323,
97
+ "<|kn|>": 50306,
98
+ "<|ko|>": 50264,
99
+ "<|la|>": 50294,
100
+ "<|lb|>": 50345,
101
+ "<|ln|>": 50353,
102
+ "<|lo|>": 50336,
103
+ "<|lt|>": 50293,
104
+ "<|lv|>": 50301,
105
+ "<|mg|>": 50349,
106
+ "<|mi|>": 50295,
107
+ "<|mk|>": 50308,
108
+ "<|ml|>": 50296,
109
+ "<|mn|>": 50314,
110
+ "<|mr|>": 50320,
111
+ "<|ms|>": 50282,
112
+ "<|mt|>": 50343,
113
+ "<|my|>": 50346,
114
+ "<|ne|>": 50313,
115
+ "<|nl|>": 50271,
116
+ "<|nn|>": 50342,
117
+ "<|no|>": 50288,
118
+ "<|oc|>": 50328,
119
+ "<|pa|>": 50321,
120
+ "<|pl|>": 50269,
121
+ "<|ps|>": 50340,
122
+ "<|pt|>": 50267,
123
+ "<|ro|>": 50284,
124
+ "<|ru|>": 50263,
125
+ "<|sa|>": 50344,
126
+ "<|sd|>": 50332,
127
+ "<|si|>": 50322,
128
+ "<|sk|>": 50298,
129
+ "<|sl|>": 50305,
130
+ "<|sn|>": 50324,
131
+ "<|so|>": 50326,
132
+ "<|sq|>": 50317,
133
+ "<|sr|>": 50303,
134
+ "<|su|>": 50357,
135
+ "<|sv|>": 50273,
136
+ "<|sw|>": 50318,
137
+ "<|ta|>": 50287,
138
+ "<|te|>": 50299,
139
+ "<|tg|>": 50331,
140
+ "<|th|>": 50289,
141
+ "<|tk|>": 50341,
142
+ "<|tl|>": 50348,
143
+ "<|tr|>": 50268,
144
+ "<|tt|>": 50351,
145
+ "<|uk|>": 50280,
146
+ "<|ur|>": 50290,
147
+ "<|uz|>": 50337,
148
+ "<|vi|>": 50278,
149
+ "<|yi|>": 50335,
150
+ "<|yo|>": 50325,
151
+ "<|zh|>": 50260
152
+ },
153
+ "language": "vi",
154
+ "max_initial_timestamp_index": 50,
155
+ "max_length": 448,
156
+ "no_timestamps_token_id": 50363,
157
+ "pad_token_id": 50257,
158
+ "prev_sot_token_id": 50361,
159
+ "return_timestamps": false,
160
+ "suppress_tokens": [
161
+ 1,
162
+ 2,
163
+ 7,
164
+ 8,
165
+ 9,
166
+ 10,
167
+ 14,
168
+ 25,
169
+ 26,
170
+ 27,
171
+ 28,
172
+ 29,
173
+ 31,
174
+ 58,
175
+ 59,
176
+ 60,
177
+ 61,
178
+ 62,
179
+ 63,
180
+ 90,
181
+ 91,
182
+ 92,
183
+ 93,
184
+ 359,
185
+ 503,
186
+ 522,
187
+ 542,
188
+ 873,
189
+ 893,
190
+ 902,
191
+ 918,
192
+ 922,
193
+ 931,
194
+ 1350,
195
+ 1853,
196
+ 1982,
197
+ 2460,
198
+ 2627,
199
+ 3246,
200
+ 3253,
201
+ 3268,
202
+ 3536,
203
+ 3846,
204
+ 3961,
205
+ 4183,
206
+ 4667,
207
+ 6585,
208
+ 6647,
209
+ 7273,
210
+ 9061,
211
+ 9383,
212
+ 10428,
213
+ 10929,
214
+ 11938,
215
+ 12033,
216
+ 12331,
217
+ 12562,
218
+ 13793,
219
+ 14157,
220
+ 14635,
221
+ 15265,
222
+ 15618,
223
+ 16553,
224
+ 16604,
225
+ 18362,
226
+ 18956,
227
+ 20075,
228
+ 21675,
229
+ 22520,
230
+ 26130,
231
+ 26161,
232
+ 26435,
233
+ 28279,
234
+ 29464,
235
+ 31650,
236
+ 32302,
237
+ 32470,
238
+ 36865,
239
+ 42863,
240
+ 47425,
241
+ 49870,
242
+ 50254,
243
+ 50258,
244
+ 50358,
245
+ 50359,
246
+ 50360,
247
+ 50361,
248
+ 50362
249
+ ],
250
+ "task": "transcribe",
251
+ "task_to_id": {
252
+ "transcribe": 50359,
253
+ "translate": 50358
254
+ },
255
+ "transformers_version": "4.39.3"
256
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ae4c867a638b3a681e9e88ffd30f20193e3dd2a95af90a99ae74e30b1d81a4e
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e1efbfe3e3e4fb4588889123ce0222c5011e289710eddc2e1ab9978a9094d8e
3
  size 966995080
runs/Nov06_10-00-54_DESKTOP-8PJSJ0N/events.out.tfevents.1730862056.DESKTOP-8PJSJ0N CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61ab20120e28259b7b1a705fb70a7416da886fe9c373683dd43470575eff9484
3
- size 23502
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed5b6d9f30d667586d83c2c5e6b01c5076f53958f01144a546db0ad31efd1e3
3
+ size 39262
runs/Nov06_16-40-03_DESKTOP-8PJSJ0N/events.out.tfevents.1730886005.DESKTOP-8PJSJ0N ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3970d223d02449d2ea5ff22bccc61661f089d0f259b042e13142d180f2964b20
3
+ size 6909
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c996f055cf78c9171ad840b3d078bccebb68e3d535e49716867473e907b9096c
3
- size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85b1b91e6412f91c0e49b3243a9c67b4aeac1f91e541b0465bda5875fbaf18f
3
+ size 5112