Hiro-nguyen commited on
Commit
74fe304
1 Parent(s): b13031d

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-medium
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-medium](https://huggingface.co/openai/whisper-medium) on the ADLINK dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0000
24
- - Wer: 33.6364
25
 
26
  ## Model description
27
 
@@ -52,18 +49,18 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Wer |
56
- |:-------------:|:-----:|:----:|:---------------:|:-------:|
57
- | 0.4926 | 25.0 | 100 | 0.1674 | 57.5758 |
58
- | 0.0002 | 50.0 | 200 | 0.0001 | 3.9394 |
59
- | 0.0001 | 75.0 | 300 | 0.0001 | 5.1515 |
60
- | 0.0001 | 100.0 | 400 | 0.0001 | 10.3030 |
61
- | 0.0001 | 125.0 | 500 | 0.0001 | 11.5152 |
62
- | 0.0 | 150.0 | 600 | 0.0000 | 28.4848 |
63
- | 0.0 | 175.0 | 700 | 0.0000 | 30.0 |
64
- | 0.0 | 200.0 | 800 | 0.0000 | 29.0909 |
65
- | 0.0 | 225.0 | 900 | 0.0000 | 33.6364 |
66
- | 0.0 | 250.0 | 1000 | 0.0000 | 33.6364 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
 
 
2
  license: apache-2.0
3
+ base_model: openai/whisper-medium.en
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.en](https://huggingface.co/openai/whisper-medium.en) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0003
21
+ - Wer: 448.7879
22
 
23
  ## Model description
24
 
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 1.1004 | 25.0 | 100 | 1.0484 | 2.1212 |
55
+ | 0.3934 | 50.0 | 200 | 0.4056 | 45.7576 |
56
+ | 0.0206 | 75.0 | 300 | 0.0131 | 63.3333 |
57
+ | 0.0012 | 100.0 | 400 | 0.0012 | 280.0 |
58
+ | 0.0006 | 125.0 | 500 | 0.0006 | 319.6970 |
59
+ | 0.0004 | 150.0 | 600 | 0.0004 | 381.5152 |
60
+ | 0.0003 | 175.0 | 700 | 0.0003 | 380.0 |
61
+ | 0.0003 | 200.0 | 800 | 0.0003 | 497.8788 |
62
+ | 0.0003 | 225.0 | 900 | 0.0003 | 462.7273 |
63
+ | 0.0003 | 250.0 | 1000 | 0.0003 | 448.7879 |
64
 
65
 
66
  ### Framework versions
generation_config.json CHANGED
@@ -1,154 +1,97 @@
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,
@@ -174,75 +117,73 @@
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
  }
 
1
  {
2
  "alignment_heads": [
3
  [
4
+ 11,
5
+ 4
6
+ ],
7
+ [
8
+ 14,
9
+ 1
10
+ ],
11
+ [
12
+ 14,
13
+ 12
14
+ ],
15
+ [
16
+ 14,
17
+ 14
18
  ],
19
  [
20
  15,
21
  4
22
  ],
23
  [
24
+ 16,
25
+ 0
26
  ],
27
  [
28
  16,
29
+ 4
30
+ ],
31
+ [
32
+ 16,
33
+ 9
34
+ ],
35
+ [
36
+ 17,
37
+ 12
38
+ ],
39
+ [
40
+ 17,
41
+ 14
42
+ ],
43
+ [
44
+ 18,
45
+ 7
46
+ ],
47
+ [
48
+ 18,
49
+ 10
50
+ ],
51
+ [
52
+ 18,
53
+ 15
54
  ],
55
  [
56
  20,
57
  0
58
  ],
59
  [
60
+ 20,
61
+ 3
62
+ ],
63
+ [
64
+ 20,
65
+ 9
66
+ ],
67
+ [
68
+ 20,
69
+ 14
70
+ ],
71
+ [
72
+ 21,
73
+ 12
74
  ]
75
  ],
76
  "begin_suppress_tokens": [
77
  220,
78
+ 50256
79
  ],
80
  "bos_token_id": 50257,
81
+ "decoder_start_token_id": 50257,
82
+ "eos_token_id": 50256,
83
  "forced_decoder_ids": [
84
  [
85
  1,
86
+ 50362
 
 
 
 
87
  ]
88
  ],
89
+ "is_multilingual": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
90
  "max_initial_timestamp_index": 50,
91
  "max_length": 448,
92
+ "no_timestamps_token_id": 50362,
93
+ "pad_token_id": 50256,
94
+ "prev_sot_token_id": 50360,
95
  "return_timestamps": false,
96
  "suppress_tokens": [
97
  1,
 
117
  91,
118
  92,
119
  93,
120
+ 357,
121
+ 366,
122
+ 438,
123
+ 532,
124
+ 685,
125
+ 705,
126
+ 796,
127
+ 930,
128
+ 1058,
129
+ 1220,
130
+ 1267,
131
+ 1279,
132
+ 1303,
133
+ 1343,
134
+ 1377,
135
+ 1391,
136
+ 1635,
137
+ 1782,
138
+ 1875,
139
+ 2162,
140
+ 2361,
141
+ 2488,
142
+ 3467,
143
+ 4008,
144
+ 4211,
145
+ 4600,
146
+ 4808,
147
+ 5299,
148
+ 5855,
149
+ 6329,
150
+ 7203,
151
+ 9609,
152
+ 9959,
153
+ 10563,
154
+ 10786,
155
+ 11420,
156
+ 11709,
157
+ 11907,
158
+ 13163,
159
+ 13697,
160
+ 13700,
161
+ 14808,
162
+ 15306,
163
+ 16410,
164
+ 16791,
165
+ 17992,
166
+ 19203,
167
+ 19510,
168
+ 20724,
169
+ 22305,
170
+ 22935,
171
+ 27007,
172
+ 30109,
173
+ 30420,
174
+ 33409,
175
+ 34949,
176
+ 40283,
177
+ 40493,
178
+ 40549,
179
+ 47282,
180
+ 49146,
181
+ 50257,
182
+ 50357,
183
  50358,
184
  50359,
185
  50360,
186
+ 50361
 
187
  ],
 
 
 
 
188
  "transformers_version": "4.41.1"
189
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e732f7fe31ae0aa5a5cdb76783718797f9e02bc29d08b9659b38492b20b7d56d
3
  size 3055540208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1739cdfa900c7abc918caedc5b8bd967376fa57c613bef9b42a3978f7a717fe9
3
  size 3055540208
runs/May29_06-01-48_z390-a/events.out.tfevents.1716966181.z390-a.1030.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e59726c3a4ed300970f66588b858007ac7d5be12ed9e4f5fd1ef93940302c5aa
3
- size 16026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4808e0b59d593307fef4007cd9fe0c606d3c0435536507f202e6fbc91684d4f6
3
+ size 17542