Hiro-nguyen commited on
Commit
52c0183
1 Parent(s): 5631c08

Model save

Browse files
README.md CHANGED
@@ -1,27 +1,24 @@
1
  ---
2
- language:
3
- - en
4
  license: apache-2.0
5
- base_model: openai/whisper-small.en
6
  tags:
7
- - hf-asr-leaderboard
8
  - generated_from_trainer
9
  metrics:
10
  - wer
11
  model-index:
12
- - name: Whisper Base EN
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 Base EN
20
 
21
- This model is a fine-tuned version of [openai/whisper-small.en](https://huggingface.co/openai/whisper-small.en) on the ADLINK dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0002
24
- - Wer: 1.5152
25
 
26
  ## Model description
27
 
@@ -52,23 +49,23 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Wer |
56
- |:-------------:|:-----:|:----:|:---------------:|:------:|
57
- | 1.1465 | 25.0 | 100 | 1.1124 | 9.6970 |
58
- | 0.4228 | 50.0 | 200 | 0.4547 | 2.4242 |
59
- | 0.0555 | 75.0 | 300 | 0.0459 | 1.8182 |
60
- | 0.0022 | 100.0 | 400 | 0.0022 | 1.8182 |
61
- | 0.0007 | 125.0 | 500 | 0.0008 | 1.5152 |
62
- | 0.0004 | 150.0 | 600 | 0.0005 | 1.5152 |
63
- | 0.0003 | 175.0 | 700 | 0.0003 | 1.5152 |
64
- | 0.0002 | 200.0 | 800 | 0.0003 | 1.5152 |
65
- | 0.0002 | 225.0 | 900 | 0.0003 | 1.5152 |
66
- | 0.0002 | 250.0 | 1000 | 0.0002 | 1.5152 |
67
 
68
 
69
  ### Framework versions
70
 
71
- - Transformers 4.41.0
72
- - Pytorch 2.2.0a0+81ea7a4
73
  - Datasets 2.19.1
74
  - Tokenizers 0.19.1
 
1
  ---
 
 
2
  license: apache-2.0
3
+ base_model: openai/whisper-medium
4
  tags:
 
5
  - generated_from_trainer
6
  metrics:
7
  - wer
8
  model-index:
9
+ - name: whisper-small-hi
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-hi
17
 
18
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0000
21
+ - Wer: 33.6364
22
 
23
  ## Model description
24
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
54
+ | 0.4926 | 25.0 | 100 | 0.1674 | 57.5758 |
55
+ | 0.0002 | 50.0 | 200 | 0.0001 | 3.9394 |
56
+ | 0.0001 | 75.0 | 300 | 0.0001 | 5.1515 |
57
+ | 0.0001 | 100.0 | 400 | 0.0001 | 10.3030 |
58
+ | 0.0001 | 125.0 | 500 | 0.0001 | 11.5152 |
59
+ | 0.0 | 150.0 | 600 | 0.0000 | 28.4848 |
60
+ | 0.0 | 175.0 | 700 | 0.0000 | 30.0 |
61
+ | 0.0 | 200.0 | 800 | 0.0000 | 29.0909 |
62
+ | 0.0 | 225.0 | 900 | 0.0000 | 33.6364 |
63
+ | 0.0 | 250.0 | 1000 | 0.0000 | 33.6364 |
64
 
65
 
66
  ### Framework versions
67
 
68
+ - Transformers 4.41.1
69
+ - Pytorch 2.3.0a0+ebedce2
70
  - Datasets 2.19.1
71
  - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -1,101 +1,155 @@
1
  {
2
  "alignment_heads": [
3
  [
4
- 6,
5
- 6
6
  ],
7
  [
8
- 7,
9
- 0
10
- ],
11
- [
12
- 7,
13
- 3
14
- ],
15
- [
16
- 7,
17
- 8
18
- ],
19
- [
20
- 8,
21
- 2
22
- ],
23
- [
24
- 8,
25
- 5
26
- ],
27
- [
28
- 8,
29
- 7
30
- ],
31
- [
32
- 9,
33
- 0
34
- ],
35
- [
36
- 9,
37
  4
38
  ],
39
  [
40
- 9,
41
- 8
42
  ],
43
  [
44
- 9,
45
- 10
46
- ],
47
- [
48
- 10,
49
- 0
50
- ],
51
- [
52
- 10,
53
  1
54
  ],
55
  [
56
- 10,
57
- 2
58
- ],
59
- [
60
- 10,
61
- 3
62
- ],
63
- [
64
- 10,
65
- 6
66
- ],
67
- [
68
- 10,
69
- 11
70
- ],
71
- [
72
- 11,
73
- 2
74
  ],
75
  [
76
- 11,
77
  4
78
  ]
79
  ],
80
  "begin_suppress_tokens": [
81
  220,
82
- 50256
83
  ],
84
  "bos_token_id": 50257,
85
- "decoder_start_token_id": 50257,
86
- "eos_token_id": 50256,
87
  "forced_decoder_ids": [
88
  [
89
  1,
90
- 50362
 
 
 
 
91
  ]
92
  ],
93
- "is_multilingual": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94
  "max_initial_timestamp_index": 50,
95
  "max_length": 448,
96
- "no_timestamps_token_id": 50362,
97
- "pad_token_id": 50256,
98
- "prev_sot_token_id": 50360,
 
99
  "suppress_tokens": [
100
  1,
101
  2,
@@ -120,73 +174,75 @@
120
  91,
121
  92,
122
  93,
123
- 357,
124
- 366,
125
- 438,
126
- 532,
127
- 685,
128
- 705,
129
- 796,
130
- 930,
131
- 1058,
132
- 1220,
133
- 1267,
134
- 1279,
135
- 1303,
136
- 1343,
137
- 1377,
138
- 1391,
139
- 1635,
140
- 1782,
141
- 1875,
142
- 2162,
143
- 2361,
144
- 2488,
145
- 3467,
146
- 4008,
147
- 4211,
148
- 4600,
149
- 4808,
150
- 5299,
151
- 5855,
152
- 6329,
153
- 7203,
154
- 9609,
155
- 9959,
156
- 10563,
157
- 10786,
158
- 11420,
159
- 11709,
160
- 11907,
161
- 13163,
162
- 13697,
163
- 13700,
164
- 14808,
165
- 15306,
166
- 16410,
167
- 16791,
168
- 17992,
169
- 19203,
170
- 19510,
171
- 20724,
172
- 22305,
173
- 22935,
174
- 27007,
175
- 30109,
176
- 30420,
177
- 33409,
178
- 34949,
179
- 40283,
180
- 40493,
181
- 40549,
182
- 47282,
183
- 49146,
184
- 50257,
185
- 50357,
186
  50358,
187
  50359,
188
  50360,
189
- 50361
 
190
  ],
191
- "transformers_version": "4.41.0"
 
 
 
 
192
  }
 
1
  {
2
  "alignment_heads": [
3
  [
4
+ 13,
5
+ 15
6
  ],
7
  [
8
+ 15,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  4
10
  ],
11
  [
12
+ 15,
13
+ 15
14
  ],
15
  [
16
+ 16,
 
 
 
 
 
 
 
 
17
  1
18
  ],
19
  [
20
+ 20,
21
+ 0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  ],
23
  [
24
+ 23,
25
  4
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
  "forced_decoder_ids": [
36
  [
37
  1,
38
+ null
39
+ ],
40
+ [
41
+ 2,
42
+ 50359
43
  ]
44
  ],
45
+ "is_multilingual": true,
46
+ "lang_to_id": {
47
+ "<|af|>": 50327,
48
+ "<|am|>": 50334,
49
+ "<|ar|>": 50272,
50
+ "<|as|>": 50350,
51
+ "<|az|>": 50304,
52
+ "<|ba|>": 50355,
53
+ "<|be|>": 50330,
54
+ "<|bg|>": 50292,
55
+ "<|bn|>": 50302,
56
+ "<|bo|>": 50347,
57
+ "<|br|>": 50309,
58
+ "<|bs|>": 50315,
59
+ "<|ca|>": 50270,
60
+ "<|cs|>": 50283,
61
+ "<|cy|>": 50297,
62
+ "<|da|>": 50285,
63
+ "<|de|>": 50261,
64
+ "<|el|>": 50281,
65
+ "<|en|>": 50259,
66
+ "<|es|>": 50262,
67
+ "<|et|>": 50307,
68
+ "<|eu|>": 50310,
69
+ "<|fa|>": 50300,
70
+ "<|fi|>": 50277,
71
+ "<|fo|>": 50338,
72
+ "<|fr|>": 50265,
73
+ "<|gl|>": 50319,
74
+ "<|gu|>": 50333,
75
+ "<|haw|>": 50352,
76
+ "<|ha|>": 50354,
77
+ "<|he|>": 50279,
78
+ "<|hi|>": 50276,
79
+ "<|hr|>": 50291,
80
+ "<|ht|>": 50339,
81
+ "<|hu|>": 50286,
82
+ "<|hy|>": 50312,
83
+ "<|id|>": 50275,
84
+ "<|is|>": 50311,
85
+ "<|it|>": 50274,
86
+ "<|ja|>": 50266,
87
+ "<|jw|>": 50356,
88
+ "<|ka|>": 50329,
89
+ "<|kk|>": 50316,
90
+ "<|km|>": 50323,
91
+ "<|kn|>": 50306,
92
+ "<|ko|>": 50264,
93
+ "<|la|>": 50294,
94
+ "<|lb|>": 50345,
95
+ "<|ln|>": 50353,
96
+ "<|lo|>": 50336,
97
+ "<|lt|>": 50293,
98
+ "<|lv|>": 50301,
99
+ "<|mg|>": 50349,
100
+ "<|mi|>": 50295,
101
+ "<|mk|>": 50308,
102
+ "<|ml|>": 50296,
103
+ "<|mn|>": 50314,
104
+ "<|mr|>": 50320,
105
+ "<|ms|>": 50282,
106
+ "<|mt|>": 50343,
107
+ "<|my|>": 50346,
108
+ "<|ne|>": 50313,
109
+ "<|nl|>": 50271,
110
+ "<|nn|>": 50342,
111
+ "<|no|>": 50288,
112
+ "<|oc|>": 50328,
113
+ "<|pa|>": 50321,
114
+ "<|pl|>": 50269,
115
+ "<|ps|>": 50340,
116
+ "<|pt|>": 50267,
117
+ "<|ro|>": 50284,
118
+ "<|ru|>": 50263,
119
+ "<|sa|>": 50344,
120
+ "<|sd|>": 50332,
121
+ "<|si|>": 50322,
122
+ "<|sk|>": 50298,
123
+ "<|sl|>": 50305,
124
+ "<|sn|>": 50324,
125
+ "<|so|>": 50326,
126
+ "<|sq|>": 50317,
127
+ "<|sr|>": 50303,
128
+ "<|su|>": 50357,
129
+ "<|sv|>": 50273,
130
+ "<|sw|>": 50318,
131
+ "<|ta|>": 50287,
132
+ "<|te|>": 50299,
133
+ "<|tg|>": 50331,
134
+ "<|th|>": 50289,
135
+ "<|tk|>": 50341,
136
+ "<|tl|>": 50348,
137
+ "<|tr|>": 50268,
138
+ "<|tt|>": 50351,
139
+ "<|uk|>": 50280,
140
+ "<|ur|>": 50290,
141
+ "<|uz|>": 50337,
142
+ "<|vi|>": 50278,
143
+ "<|yi|>": 50335,
144
+ "<|yo|>": 50325,
145
+ "<|zh|>": 50260
146
+ },
147
  "max_initial_timestamp_index": 50,
148
  "max_length": 448,
149
+ "no_timestamps_token_id": 50363,
150
+ "pad_token_id": 50257,
151
+ "prev_sot_token_id": 50361,
152
+ "return_timestamps": false,
153
  "suppress_tokens": [
154
  1,
155
  2,
 
174
  91,
175
  92,
176
  93,
177
+ 359,
178
+ 503,
179
+ 522,
180
+ 542,
181
+ 873,
182
+ 893,
183
+ 902,
184
+ 918,
185
+ 922,
186
+ 931,
187
+ 1350,
188
+ 1853,
189
+ 1982,
190
+ 2460,
191
+ 2627,
192
+ 3246,
193
+ 3253,
194
+ 3268,
195
+ 3536,
196
+ 3846,
197
+ 3961,
198
+ 4183,
199
+ 4667,
200
+ 6585,
201
+ 6647,
202
+ 7273,
203
+ 9061,
204
+ 9383,
205
+ 10428,
206
+ 10929,
207
+ 11938,
208
+ 12033,
209
+ 12331,
210
+ 12562,
211
+ 13793,
212
+ 14157,
213
+ 14635,
214
+ 15265,
215
+ 15618,
216
+ 16553,
217
+ 16604,
218
+ 18362,
219
+ 18956,
220
+ 20075,
221
+ 21675,
222
+ 22520,
223
+ 26130,
224
+ 26161,
225
+ 26435,
226
+ 28279,
227
+ 29464,
228
+ 31650,
229
+ 32302,
230
+ 32470,
231
+ 36865,
232
+ 42863,
233
+ 47425,
234
+ 49870,
235
+ 50254,
236
+ 50258,
 
 
 
237
  50358,
238
  50359,
239
  50360,
240
+ 50361,
241
+ 50362
242
  ],
243
+ "task_to_id": {
244
+ "transcribe": 50359,
245
+ "translate": 50358
246
+ },
247
+ "transformers_version": "4.41.1"
248
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1abe918fb1f7d133daf5c52a33fab9807cdcd7dbcead77c25fdfed3026115512
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fca60706c7669158d40f8968b3dd6912942bcd506317b3b5bc9a1b3d3399cd1
3
  size 3055544304
runs/May29_02-48-36_z390-a/events.out.tfevents.1716950927.z390-a.790.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb008d8093129260d8ae4d947d1bdb714da32afbf6885c6afdccd521674568b3
3
- size 14861
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22c603edbdc3c426a22f71cb554c23c6fa83f38df879776a949260e15b6b2f14
3
+ size 17539