Malavita commited on
Commit
28f2ebd
1 Parent(s): 9ca8ecf

Upload WhisperForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +3 -3
  2. config.json +12 -2
  3. generation_config.json +256 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -12,8 +12,8 @@ model-index:
12
  - name: openai/whisper-medium
13
  results:
14
  - task:
15
- name: Automatic Speech Recognition
16
  type: automatic-speech-recognition
 
17
  dataset:
18
  name: mozilla-foundation/common_voice_11_0
19
  type: mozilla-foundation/common_voice_11_0
@@ -21,9 +21,9 @@ model-index:
21
  split: test
22
  args: pt
23
  metrics:
24
- - name: Wer
25
- type: wer
26
  value: 6.598745817992301
 
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
12
  - name: openai/whisper-medium
13
  results:
14
  - task:
 
15
  type: automatic-speech-recognition
16
+ name: Automatic Speech Recognition
17
  dataset:
18
  name: mozilla-foundation/common_voice_11_0
19
  type: mozilla-foundation/common_voice_11_0
 
21
  split: test
22
  args: pt
23
  metrics:
24
+ - type: wer
 
25
  value: 6.598745817992301
26
+ name: Wer
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
config.json CHANGED
@@ -1,7 +1,8 @@
1
  {
2
- "_name_or_path": "openai/whisper-medium",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
 
5
  "architectures": [
6
  "WhisperForConditionalGeneration"
7
  ],
@@ -11,6 +12,7 @@
11
  50257
12
  ],
13
  "bos_token_id": 50257,
 
14
  "d_model": 1024,
15
  "decoder_attention_heads": 16,
16
  "decoder_ffn_dim": 4096,
@@ -26,16 +28,24 @@
26
  "forced_decoder_ids": null,
27
  "init_std": 0.02,
28
  "is_encoder_decoder": true,
 
 
 
 
 
 
29
  "max_length": 448,
30
  "max_source_positions": 1500,
31
  "max_target_positions": 448,
 
32
  "model_type": "whisper",
33
  "num_hidden_layers": 24,
34
  "num_mel_bins": 80,
35
  "pad_token_id": 50257,
36
  "scale_embedding": false,
37
  "torch_dtype": "float32",
38
- "transformers_version": "4.26.0.dev0",
39
  "use_cache": false,
 
40
  "vocab_size": 51865
41
  }
 
1
  {
2
+ "_name_or_path": "pierreguillou/whisper-medium-portuguese",
3
  "activation_dropout": 0.0,
4
  "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
  "architectures": [
7
  "WhisperForConditionalGeneration"
8
  ],
 
12
  50257
13
  ],
14
  "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
  "d_model": 1024,
17
  "decoder_attention_heads": 16,
18
  "decoder_ffn_dim": 4096,
 
28
  "forced_decoder_ids": null,
29
  "init_std": 0.02,
30
  "is_encoder_decoder": true,
31
+ "mask_feature_length": 10,
32
+ "mask_feature_min_masks": 0,
33
+ "mask_feature_prob": 0.0,
34
+ "mask_time_length": 10,
35
+ "mask_time_min_masks": 2,
36
+ "mask_time_prob": 0.05,
37
  "max_length": 448,
38
  "max_source_positions": 1500,
39
  "max_target_positions": 448,
40
+ "median_filter_width": 7,
41
  "model_type": "whisper",
42
  "num_hidden_layers": 24,
43
  "num_mel_bins": 80,
44
  "pad_token_id": 50257,
45
  "scale_embedding": false,
46
  "torch_dtype": "float32",
47
+ "transformers_version": "4.38.1",
48
  "use_cache": false,
49
+ "use_weighted_layer_sum": false,
50
  "vocab_size": 51865
51
  }
generation_config.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "forced_decoder_ids": [
44
+ [
45
+ 1,
46
+ null
47
+ ],
48
+ [
49
+ 2,
50
+ 50359
51
+ ]
52
+ ],
53
+ "is_multilingual": true,
54
+ "lang_to_id": {
55
+ "<|af|>": 50327,
56
+ "<|am|>": 50334,
57
+ "<|ar|>": 50272,
58
+ "<|as|>": 50350,
59
+ "<|az|>": 50304,
60
+ "<|ba|>": 50355,
61
+ "<|be|>": 50330,
62
+ "<|bg|>": 50292,
63
+ "<|bn|>": 50302,
64
+ "<|bo|>": 50347,
65
+ "<|br|>": 50309,
66
+ "<|bs|>": 50315,
67
+ "<|ca|>": 50270,
68
+ "<|cs|>": 50283,
69
+ "<|cy|>": 50297,
70
+ "<|da|>": 50285,
71
+ "<|de|>": 50261,
72
+ "<|el|>": 50281,
73
+ "<|en|>": 50259,
74
+ "<|es|>": 50262,
75
+ "<|et|>": 50307,
76
+ "<|eu|>": 50310,
77
+ "<|fa|>": 50300,
78
+ "<|fi|>": 50277,
79
+ "<|fo|>": 50338,
80
+ "<|fr|>": 50265,
81
+ "<|gl|>": 50319,
82
+ "<|gu|>": 50333,
83
+ "<|haw|>": 50352,
84
+ "<|ha|>": 50354,
85
+ "<|he|>": 50279,
86
+ "<|hi|>": 50276,
87
+ "<|hr|>": 50291,
88
+ "<|ht|>": 50339,
89
+ "<|hu|>": 50286,
90
+ "<|hy|>": 50312,
91
+ "<|id|>": 50275,
92
+ "<|is|>": 50311,
93
+ "<|it|>": 50274,
94
+ "<|ja|>": 50266,
95
+ "<|jw|>": 50356,
96
+ "<|ka|>": 50329,
97
+ "<|kk|>": 50316,
98
+ "<|km|>": 50323,
99
+ "<|kn|>": 50306,
100
+ "<|ko|>": 50264,
101
+ "<|la|>": 50294,
102
+ "<|lb|>": 50345,
103
+ "<|ln|>": 50353,
104
+ "<|lo|>": 50336,
105
+ "<|lt|>": 50293,
106
+ "<|lv|>": 50301,
107
+ "<|mg|>": 50349,
108
+ "<|mi|>": 50295,
109
+ "<|mk|>": 50308,
110
+ "<|ml|>": 50296,
111
+ "<|mn|>": 50314,
112
+ "<|mr|>": 50320,
113
+ "<|ms|>": 50282,
114
+ "<|mt|>": 50343,
115
+ "<|my|>": 50346,
116
+ "<|ne|>": 50313,
117
+ "<|nl|>": 50271,
118
+ "<|nn|>": 50342,
119
+ "<|no|>": 50288,
120
+ "<|oc|>": 50328,
121
+ "<|pa|>": 50321,
122
+ "<|pl|>": 50269,
123
+ "<|ps|>": 50340,
124
+ "<|pt|>": 50267,
125
+ "<|ro|>": 50284,
126
+ "<|ru|>": 50263,
127
+ "<|sa|>": 50344,
128
+ "<|sd|>": 50332,
129
+ "<|si|>": 50322,
130
+ "<|sk|>": 50298,
131
+ "<|sl|>": 50305,
132
+ "<|sn|>": 50324,
133
+ "<|so|>": 50326,
134
+ "<|sq|>": 50317,
135
+ "<|sr|>": 50303,
136
+ "<|su|>": 50357,
137
+ "<|sv|>": 50273,
138
+ "<|sw|>": 50318,
139
+ "<|ta|>": 50287,
140
+ "<|te|>": 50299,
141
+ "<|tg|>": 50331,
142
+ "<|th|>": 50289,
143
+ "<|tk|>": 50341,
144
+ "<|tl|>": 50348,
145
+ "<|tr|>": 50268,
146
+ "<|tt|>": 50351,
147
+ "<|uk|>": 50280,
148
+ "<|ur|>": 50290,
149
+ "<|uz|>": 50337,
150
+ "<|vi|>": 50278,
151
+ "<|yi|>": 50335,
152
+ "<|yo|>": 50325,
153
+ "<|zh|>": 50260
154
+ },
155
+ "max_initial_timestamp_index": 50,
156
+ "max_length": 448,
157
+ "no_timestamps_token_id": 50363,
158
+ "pad_token_id": 50257,
159
+ "prev_sot_token_id": 50361,
160
+ "return_timestamps": false,
161
+ "suppress_tokens": [
162
+ 1,
163
+ 2,
164
+ 7,
165
+ 8,
166
+ 9,
167
+ 10,
168
+ 14,
169
+ 25,
170
+ 26,
171
+ 27,
172
+ 28,
173
+ 29,
174
+ 31,
175
+ 58,
176
+ 59,
177
+ 60,
178
+ 61,
179
+ 62,
180
+ 63,
181
+ 90,
182
+ 91,
183
+ 92,
184
+ 93,
185
+ 359,
186
+ 503,
187
+ 522,
188
+ 542,
189
+ 873,
190
+ 893,
191
+ 902,
192
+ 918,
193
+ 922,
194
+ 931,
195
+ 1350,
196
+ 1853,
197
+ 1982,
198
+ 2460,
199
+ 2627,
200
+ 3246,
201
+ 3253,
202
+ 3268,
203
+ 3536,
204
+ 3846,
205
+ 3961,
206
+ 4183,
207
+ 4667,
208
+ 6585,
209
+ 6647,
210
+ 7273,
211
+ 9061,
212
+ 9383,
213
+ 10428,
214
+ 10929,
215
+ 11938,
216
+ 12033,
217
+ 12331,
218
+ 12562,
219
+ 13793,
220
+ 14157,
221
+ 14635,
222
+ 15265,
223
+ 15618,
224
+ 16553,
225
+ 16604,
226
+ 18362,
227
+ 18956,
228
+ 20075,
229
+ 21675,
230
+ 22520,
231
+ 26130,
232
+ 26161,
233
+ 26435,
234
+ 28279,
235
+ 29464,
236
+ 31650,
237
+ 32302,
238
+ 32470,
239
+ 36865,
240
+ 42863,
241
+ 47425,
242
+ 49870,
243
+ 50254,
244
+ 50258,
245
+ 50358,
246
+ 50359,
247
+ 50360,
248
+ 50361,
249
+ 50362
250
+ ],
251
+ "task_to_id": {
252
+ "transcribe": 50359,
253
+ "translate": 50358
254
+ },
255
+ "transformers_version": "4.38.1"
256
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fecc00259f879b65d35ae190c010a39a31e835581131c63c1b47fe69cc1df52
3
+ size 3055544304