Tejnaresh commited on
Commit
6a0201a
·
verified ·
1 Parent(s): d125713

End of training

Browse files
Files changed (2) hide show
  1. README.md +25 -4
  2. generation_config.json +189 -86
README.md CHANGED
@@ -7,17 +7,35 @@ tags:
7
  - generated_from_trainer
8
  datasets:
9
  - mozilla-foundation/common_voice_11_0
 
 
10
  model-index:
11
- - name: Whisper Tiny En - Teja Naresh
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 Tiny En - Teja Naresh
19
 
20
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
 
 
 
21
 
22
  ## Model description
23
 
@@ -45,11 +63,14 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
48
- - training_steps: 500
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
 
 
 
53
 
54
 
55
  ### Framework versions
 
7
  - generated_from_trainer
8
  datasets:
9
  - mozilla-foundation/common_voice_11_0
10
+ metrics:
11
+ - wer
12
  model-index:
13
+ - name: Whisper Small Hi - Sanchit Gandhi
14
+ results:
15
+ - task:
16
+ name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
+ dataset:
19
+ name: Common Voice 11.0
20
+ type: mozilla-foundation/common_voice_11_0
21
+ config: hi
22
+ split: None
23
+ args: 'config: hi, split: test'
24
+ metrics:
25
+ - name: Wer
26
+ type: wer
27
+ value: 49.157707610259884
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
  should probably proofread and complete it, then remove this comment. -->
32
 
33
+ # Whisper Small Hi - Sanchit Gandhi
34
 
35
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
36
+ It achieves the following results on the evaluation set:
37
+ - Loss: 0.4219
38
+ - Wer: 49.1577
39
 
40
  ## Model description
41
 
 
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: linear
65
  - lr_scheduler_warmup_steps: 500
66
+ - training_steps: 1000
67
  - mixed_precision_training: Native AMP
68
 
69
  ### Training results
70
 
71
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
72
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
73
+ | 0.2156 | 2.44 | 1000 | 0.4219 | 49.1577 |
74
 
75
 
76
  ### Framework versions
generation_config.json CHANGED
@@ -1,52 +1,153 @@
1
  {
2
  "alignment_heads": [
3
  [
4
- 1,
5
- 0
6
  ],
7
  [
8
- 2,
9
- 0
10
  ],
11
  [
12
- 2,
13
- 5
14
  ],
15
  [
16
- 3,
17
- 0
18
  ],
19
  [
20
- 3,
21
  1
22
  ],
23
  [
24
- 3,
25
  2
26
  ],
27
  [
28
- 3,
29
- 3
30
  ],
31
  [
32
- 3,
33
- 4
34
  ]
35
  ],
36
  "begin_suppress_tokens": [
37
  220,
38
- 50256
39
  ],
40
  "bos_token_id": 50257,
41
- "decoder_start_token_id": 50257,
42
- "eos_token_id": 50256,
43
- "is_multilingual": false,
44
- "language": "English",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  "max_initial_timestamp_index": 50,
46
  "max_length": 448,
47
- "no_timestamps_token_id": 50362,
48
- "pad_token_id": 50256,
49
- "prev_sot_token_id": 50360,
50
  "return_timestamps": false,
51
  "suppress_tokens": [
52
  1,
@@ -72,74 +173,76 @@
72
  91,
73
  92,
74
  93,
75
- 357,
76
- 366,
77
- 438,
78
- 532,
79
- 685,
80
- 705,
81
- 796,
82
- 930,
83
- 1058,
84
- 1220,
85
- 1267,
86
- 1279,
87
- 1303,
88
- 1343,
89
- 1377,
90
- 1391,
91
- 1635,
92
- 1782,
93
- 1875,
94
- 2162,
95
- 2361,
96
- 2488,
97
- 3467,
98
- 4008,
99
- 4211,
100
- 4600,
101
- 4808,
102
- 5299,
103
- 5855,
104
- 6329,
105
- 7203,
106
- 9609,
107
- 9959,
108
- 10563,
109
- 10786,
110
- 11420,
111
- 11709,
112
- 11907,
113
- 13163,
114
- 13697,
115
- 13700,
116
- 14808,
117
- 15306,
118
- 16410,
119
- 16791,
120
- 17992,
121
- 19203,
122
- 19510,
123
- 20724,
124
- 22305,
125
- 22935,
126
- 27007,
127
- 30109,
128
- 30420,
129
- 33409,
130
- 34949,
131
- 40283,
132
- 40493,
133
- 40549,
134
- 47282,
135
- 49146,
136
- 50257,
137
- 50357,
138
  50358,
139
  50359,
140
  50360,
141
- 50361
 
142
  ],
143
  "task": "transcribe",
 
 
 
 
144
  "transformers_version": "4.39.3"
145
  }
 
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": "telugu",
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,
 
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": "4.39.3"
248
  }