steja commited on
Commit
f883800
1 Parent(s): 5d2ef29

Model save

Browse files
Files changed (3) hide show
  1. README.md +23 -24
  2. generation_config.json +264 -0
  3. model.safetensors +1 -1
README.md CHANGED
@@ -1,38 +1,39 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
- - whisper-event
5
  - generated_from_trainer
6
  datasets:
7
- - google/fleurs
8
  metrics:
9
  - wer
10
  model-index:
11
- - name: Whisper_small_Shona
12
  results:
13
  - task:
14
  name: Automatic Speech Recognition
15
  type: automatic-speech-recognition
16
  dataset:
17
- name: google/fleurs
18
- type: google/fleurs
19
  config: sn_zw
20
  split: test
 
21
  metrics:
22
  - name: Wer
23
  type: wer
24
- value: 50.85625
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
  should probably proofread and complete it, then remove this comment. -->
29
 
30
- # Whisper_small_Shona
31
 
32
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the google/fleurs sn_zw dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 1.1174
35
- - Wer: 50.8563
36
 
37
  ## Model description
38
 
@@ -56,10 +57,8 @@ The following hyperparameters were used during training:
56
  - eval_batch_size: 16
57
  - seed: 42
58
  - distributed_type: multi-GPU
59
- - num_devices: 4
60
  - gradient_accumulation_steps: 2
61
- - total_train_batch_size: 64
62
- - total_eval_batch_size: 64
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: linear
65
  - lr_scheduler_warmup_steps: 500
@@ -68,18 +67,18 @@ The following hyperparameters were used during training:
68
 
69
  ### Training results
70
 
71
- | Training Loss | Epoch | Step | Validation Loss | Wer |
72
- |:-------------:|:------:|:----:|:---------------:|:-------:|
73
- | 0.0054 | 33.32 | 400 | 0.9826 | 51.6687 |
74
- | 0.0009 | 66.64 | 800 | 1.0774 | 50.9062 |
75
- | 0.0005 | 99.96 | 1200 | 1.1174 | 50.8563 |
76
- | 0.0003 | 133.32 | 1600 | 1.1388 | 50.875 |
77
- | 0.0003 | 166.64 | 2000 | 1.1461 | 50.925 |
78
 
79
 
80
  ### Framework versions
81
 
82
- - Transformers 4.25.1
83
- - Pytorch 1.13.0+cu117
84
- - Datasets 2.7.1
85
- - Tokenizers 0.13.2
 
1
  ---
2
  license: apache-2.0
3
+ base_model: openai/whisper-small
4
  tags:
 
5
  - generated_from_trainer
6
  datasets:
7
+ - fleurs
8
  metrics:
9
  - wer
10
  model-index:
11
+ - name: whisper-small-shona
12
  results:
13
  - task:
14
  name: Automatic Speech Recognition
15
  type: automatic-speech-recognition
16
  dataset:
17
+ name: fleurs
18
+ type: fleurs
19
  config: sn_zw
20
  split: test
21
+ args: sn_zw
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 45.94375
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
+ # whisper-small-shona
32
 
33
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the fleurs dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.9720
36
+ - Wer: 45.9438
37
 
38
  ## Model description
39
 
 
57
  - eval_batch_size: 16
58
  - seed: 42
59
  - distributed_type: multi-GPU
 
60
  - gradient_accumulation_steps: 2
61
+ - total_train_batch_size: 16
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_steps: 500
 
67
 
68
  ### Training results
69
 
70
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
71
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
72
+ | 0.09 | 8.16 | 400 | 0.8572 | 50.6875 |
73
+ | 0.0019 | 16.33 | 800 | 0.9069 | 46.4438 |
74
+ | 0.0008 | 24.49 | 1200 | 0.9473 | 46.0438 |
75
+ | 0.0006 | 32.65 | 1600 | 0.9653 | 45.9 |
76
+ | 0.0005 | 40.82 | 2000 | 0.9720 | 45.9438 |
77
 
78
 
79
  ### Framework versions
80
 
81
+ - Transformers 4.37.1
82
+ - Pytorch 1.12.0+cu102
83
+ - Datasets 2.16.1
84
+ - Tokenizers 0.15.1
generation_config.json ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "forced_decoder_ids": [
52
+ [
53
+ 1,
54
+ null
55
+ ],
56
+ [
57
+ 2,
58
+ 50359
59
+ ]
60
+ ],
61
+ "is_multilingual": true,
62
+ "lang_to_id": {
63
+ "<|af|>": 50327,
64
+ "<|am|>": 50334,
65
+ "<|ar|>": 50272,
66
+ "<|as|>": 50350,
67
+ "<|az|>": 50304,
68
+ "<|ba|>": 50355,
69
+ "<|be|>": 50330,
70
+ "<|bg|>": 50292,
71
+ "<|bn|>": 50302,
72
+ "<|bo|>": 50347,
73
+ "<|br|>": 50309,
74
+ "<|bs|>": 50315,
75
+ "<|ca|>": 50270,
76
+ "<|cs|>": 50283,
77
+ "<|cy|>": 50297,
78
+ "<|da|>": 50285,
79
+ "<|de|>": 50261,
80
+ "<|el|>": 50281,
81
+ "<|en|>": 50259,
82
+ "<|es|>": 50262,
83
+ "<|et|>": 50307,
84
+ "<|eu|>": 50310,
85
+ "<|fa|>": 50300,
86
+ "<|fi|>": 50277,
87
+ "<|fo|>": 50338,
88
+ "<|fr|>": 50265,
89
+ "<|gl|>": 50319,
90
+ "<|gu|>": 50333,
91
+ "<|haw|>": 50352,
92
+ "<|ha|>": 50354,
93
+ "<|he|>": 50279,
94
+ "<|hi|>": 50276,
95
+ "<|hr|>": 50291,
96
+ "<|ht|>": 50339,
97
+ "<|hu|>": 50286,
98
+ "<|hy|>": 50312,
99
+ "<|id|>": 50275,
100
+ "<|is|>": 50311,
101
+ "<|it|>": 50274,
102
+ "<|ja|>": 50266,
103
+ "<|jw|>": 50356,
104
+ "<|ka|>": 50329,
105
+ "<|kk|>": 50316,
106
+ "<|km|>": 50323,
107
+ "<|kn|>": 50306,
108
+ "<|ko|>": 50264,
109
+ "<|la|>": 50294,
110
+ "<|lb|>": 50345,
111
+ "<|ln|>": 50353,
112
+ "<|lo|>": 50336,
113
+ "<|lt|>": 50293,
114
+ "<|lv|>": 50301,
115
+ "<|mg|>": 50349,
116
+ "<|mi|>": 50295,
117
+ "<|mk|>": 50308,
118
+ "<|ml|>": 50296,
119
+ "<|mn|>": 50314,
120
+ "<|mr|>": 50320,
121
+ "<|ms|>": 50282,
122
+ "<|mt|>": 50343,
123
+ "<|my|>": 50346,
124
+ "<|ne|>": 50313,
125
+ "<|nl|>": 50271,
126
+ "<|nn|>": 50342,
127
+ "<|no|>": 50288,
128
+ "<|oc|>": 50328,
129
+ "<|pa|>": 50321,
130
+ "<|pl|>": 50269,
131
+ "<|ps|>": 50340,
132
+ "<|pt|>": 50267,
133
+ "<|ro|>": 50284,
134
+ "<|ru|>": 50263,
135
+ "<|sa|>": 50344,
136
+ "<|sd|>": 50332,
137
+ "<|si|>": 50322,
138
+ "<|sk|>": 50298,
139
+ "<|sl|>": 50305,
140
+ "<|sn|>": 50324,
141
+ "<|so|>": 50326,
142
+ "<|sq|>": 50317,
143
+ "<|sr|>": 50303,
144
+ "<|su|>": 50357,
145
+ "<|sv|>": 50273,
146
+ "<|sw|>": 50318,
147
+ "<|ta|>": 50287,
148
+ "<|te|>": 50299,
149
+ "<|tg|>": 50331,
150
+ "<|th|>": 50289,
151
+ "<|tk|>": 50341,
152
+ "<|tl|>": 50348,
153
+ "<|tr|>": 50268,
154
+ "<|tt|>": 50351,
155
+ "<|uk|>": 50280,
156
+ "<|ur|>": 50290,
157
+ "<|uz|>": 50337,
158
+ "<|vi|>": 50278,
159
+ "<|yi|>": 50335,
160
+ "<|yo|>": 50325,
161
+ "<|zh|>": 50260
162
+ },
163
+ "max_initial_timestamp_index": 50,
164
+ "max_length": 448,
165
+ "no_timestamps_token_id": 50363,
166
+ "pad_token_id": 50257,
167
+ "prev_sot_token_id": 50361,
168
+ "return_timestamps": false,
169
+ "suppress_tokens": [
170
+ 1,
171
+ 2,
172
+ 7,
173
+ 8,
174
+ 9,
175
+ 10,
176
+ 14,
177
+ 25,
178
+ 26,
179
+ 27,
180
+ 28,
181
+ 29,
182
+ 31,
183
+ 58,
184
+ 59,
185
+ 60,
186
+ 61,
187
+ 62,
188
+ 63,
189
+ 90,
190
+ 91,
191
+ 92,
192
+ 93,
193
+ 359,
194
+ 503,
195
+ 522,
196
+ 542,
197
+ 873,
198
+ 893,
199
+ 902,
200
+ 918,
201
+ 922,
202
+ 931,
203
+ 1350,
204
+ 1853,
205
+ 1982,
206
+ 2460,
207
+ 2627,
208
+ 3246,
209
+ 3253,
210
+ 3268,
211
+ 3536,
212
+ 3846,
213
+ 3961,
214
+ 4183,
215
+ 4667,
216
+ 6585,
217
+ 6647,
218
+ 7273,
219
+ 9061,
220
+ 9383,
221
+ 10428,
222
+ 10929,
223
+ 11938,
224
+ 12033,
225
+ 12331,
226
+ 12562,
227
+ 13793,
228
+ 14157,
229
+ 14635,
230
+ 15265,
231
+ 15618,
232
+ 16553,
233
+ 16604,
234
+ 18362,
235
+ 18956,
236
+ 20075,
237
+ 21675,
238
+ 22520,
239
+ 26130,
240
+ 26161,
241
+ 26435,
242
+ 28279,
243
+ 29464,
244
+ 31650,
245
+ 32302,
246
+ 32470,
247
+ 36865,
248
+ 42863,
249
+ 47425,
250
+ 49870,
251
+ 50254,
252
+ 50258,
253
+ 50358,
254
+ 50359,
255
+ 50360,
256
+ 50361,
257
+ 50362
258
+ ],
259
+ "task_to_id": {
260
+ "transcribe": 50359,
261
+ "translate": 50358
262
+ },
263
+ "transformers_version": "4.37.1"
264
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bbbb3cb5c08d7278d9bda9baf1f95628a43137ccca58b044522c6bdf018a171
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a7bdd83a81fc26df3c33205dba70207cd30d7d5821b7ee53c1dcd8f1609c139
3
  size 966995080