nurenora commited on
Commit
fa1437e
1 Parent(s): 994f4b2

Model save

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json CHANGED
@@ -17,7 +17,6 @@
17
  "<|da|>": 50285,
18
  "<|de|>": 50261,
19
  "<|el|>": 50281,
20
- "<|endoftext|>": 50257,
21
  "<|en|>": 50259,
22
  "<|es|>": 50262,
23
  "<|et|>": 50307,
@@ -30,6 +29,7 @@
30
  "<|gu|>": 50333,
31
  "<|haw|>": 50352,
32
  "<|ha|>": 50354,
 
33
  "<|hi|>": 50276,
34
  "<|hr|>": 50291,
35
  "<|ht|>": 50339,
@@ -38,7 +38,6 @@
38
  "<|id|>": 50275,
39
  "<|is|>": 50311,
40
  "<|it|>": 50274,
41
- "<|iw|>": 50279,
42
  "<|ja|>": 50266,
43
  "<|jw|>": 50356,
44
  "<|ka|>": 50329,
 
17
  "<|da|>": 50285,
18
  "<|de|>": 50261,
19
  "<|el|>": 50281,
 
20
  "<|en|>": 50259,
21
  "<|es|>": 50262,
22
  "<|et|>": 50307,
 
29
  "<|gu|>": 50333,
30
  "<|haw|>": 50352,
31
  "<|ha|>": 50354,
32
+ "<|he|>": 50279,
33
  "<|hi|>": 50276,
34
  "<|hr|>": 50291,
35
  "<|ht|>": 50339,
 
38
  "<|id|>": 50275,
39
  "<|is|>": 50311,
40
  "<|it|>": 50274,
 
41
  "<|ja|>": 50266,
42
  "<|jw|>": 50356,
43
  "<|ka|>": 50329,
config.json CHANGED
@@ -2,6 +2,7 @@
2
  "_name_or_path": "openai/whisper-tiny",
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": 384,
15
  "decoder_attention_heads": 6,
16
  "decoder_ffn_dim": 1536,
@@ -26,6 +28,12 @@
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,
@@ -36,7 +44,8 @@
36
  "scale_embedding": false,
37
  "suppress_tokens": [],
38
  "torch_dtype": "float32",
39
- "transformers_version": "4.26.0.dev0",
40
  "use_cache": false,
 
41
  "vocab_size": 51865
42
  }
 
2
  "_name_or_path": "openai/whisper-tiny",
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": 384,
17
  "decoder_attention_heads": 6,
18
  "decoder_ffn_dim": 1536,
 
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,
 
44
  "scale_embedding": false,
45
  "suppress_tokens": [],
46
  "torch_dtype": "float32",
47
+ "transformers_version": "4.28.0",
48
  "use_cache": false,
49
+ "use_weighted_layer_sum": false,
50
  "vocab_size": 51865
51
  }
generation_config.json ADDED
@@ -0,0 +1,222 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "begin_suppress_tokens": [
3
+ 220,
4
+ 50257
5
+ ],
6
+ "bos_token_id": 50257,
7
+ "decoder_start_token_id": 50258,
8
+ "eos_token_id": 50257,
9
+ "forced_decoder_ids": [
10
+ [
11
+ 1,
12
+ null
13
+ ],
14
+ [
15
+ 2,
16
+ 50359
17
+ ]
18
+ ],
19
+ "is_multilingual": true,
20
+ "lang_to_id": {
21
+ "<|af|>": 50327,
22
+ "<|am|>": 50334,
23
+ "<|ar|>": 50272,
24
+ "<|as|>": 50350,
25
+ "<|az|>": 50304,
26
+ "<|ba|>": 50355,
27
+ "<|be|>": 50330,
28
+ "<|bg|>": 50292,
29
+ "<|bn|>": 50302,
30
+ "<|bo|>": 50347,
31
+ "<|br|>": 50309,
32
+ "<|bs|>": 50315,
33
+ "<|ca|>": 50270,
34
+ "<|cs|>": 50283,
35
+ "<|cy|>": 50297,
36
+ "<|da|>": 50285,
37
+ "<|de|>": 50261,
38
+ "<|el|>": 50281,
39
+ "<|en|>": 50259,
40
+ "<|es|>": 50262,
41
+ "<|et|>": 50307,
42
+ "<|eu|>": 50310,
43
+ "<|fa|>": 50300,
44
+ "<|fi|>": 50277,
45
+ "<|fo|>": 50338,
46
+ "<|fr|>": 50265,
47
+ "<|gl|>": 50319,
48
+ "<|gu|>": 50333,
49
+ "<|haw|>": 50352,
50
+ "<|ha|>": 50354,
51
+ "<|he|>": 50279,
52
+ "<|hi|>": 50276,
53
+ "<|hr|>": 50291,
54
+ "<|ht|>": 50339,
55
+ "<|hu|>": 50286,
56
+ "<|hy|>": 50312,
57
+ "<|id|>": 50275,
58
+ "<|is|>": 50311,
59
+ "<|it|>": 50274,
60
+ "<|ja|>": 50266,
61
+ "<|jw|>": 50356,
62
+ "<|ka|>": 50329,
63
+ "<|kk|>": 50316,
64
+ "<|km|>": 50323,
65
+ "<|kn|>": 50306,
66
+ "<|ko|>": 50264,
67
+ "<|la|>": 50294,
68
+ "<|lb|>": 50345,
69
+ "<|ln|>": 50353,
70
+ "<|lo|>": 50336,
71
+ "<|lt|>": 50293,
72
+ "<|lv|>": 50301,
73
+ "<|mg|>": 50349,
74
+ "<|mi|>": 50295,
75
+ "<|mk|>": 50308,
76
+ "<|ml|>": 50296,
77
+ "<|mn|>": 50314,
78
+ "<|mr|>": 50320,
79
+ "<|ms|>": 50282,
80
+ "<|mt|>": 50343,
81
+ "<|my|>": 50346,
82
+ "<|ne|>": 50313,
83
+ "<|nl|>": 50271,
84
+ "<|nn|>": 50342,
85
+ "<|no|>": 50288,
86
+ "<|oc|>": 50328,
87
+ "<|pa|>": 50321,
88
+ "<|pl|>": 50269,
89
+ "<|ps|>": 50340,
90
+ "<|pt|>": 50267,
91
+ "<|ro|>": 50284,
92
+ "<|ru|>": 50263,
93
+ "<|sa|>": 50344,
94
+ "<|sd|>": 50332,
95
+ "<|si|>": 50322,
96
+ "<|sk|>": 50298,
97
+ "<|sl|>": 50305,
98
+ "<|sn|>": 50324,
99
+ "<|so|>": 50326,
100
+ "<|sq|>": 50317,
101
+ "<|sr|>": 50303,
102
+ "<|su|>": 50357,
103
+ "<|sv|>": 50273,
104
+ "<|sw|>": 50318,
105
+ "<|ta|>": 50287,
106
+ "<|te|>": 50299,
107
+ "<|tg|>": 50331,
108
+ "<|th|>": 50289,
109
+ "<|tk|>": 50341,
110
+ "<|tl|>": 50348,
111
+ "<|tr|>": 50268,
112
+ "<|tt|>": 50351,
113
+ "<|uk|>": 50280,
114
+ "<|ur|>": 50290,
115
+ "<|uz|>": 50337,
116
+ "<|vi|>": 50278,
117
+ "<|yi|>": 50335,
118
+ "<|yo|>": 50325,
119
+ "<|zh|>": 50260
120
+ },
121
+ "max_initial_timestamp_index": 1,
122
+ "max_length": 448,
123
+ "no_timestamps_token_id": 50363,
124
+ "pad_token_id": 50257,
125
+ "return_timestamps": false,
126
+ "suppress_tokens": [
127
+ 1,
128
+ 2,
129
+ 7,
130
+ 8,
131
+ 9,
132
+ 10,
133
+ 14,
134
+ 25,
135
+ 26,
136
+ 27,
137
+ 28,
138
+ 29,
139
+ 31,
140
+ 58,
141
+ 59,
142
+ 60,
143
+ 61,
144
+ 62,
145
+ 63,
146
+ 90,
147
+ 91,
148
+ 92,
149
+ 93,
150
+ 359,
151
+ 503,
152
+ 522,
153
+ 542,
154
+ 873,
155
+ 893,
156
+ 902,
157
+ 918,
158
+ 922,
159
+ 931,
160
+ 1350,
161
+ 1853,
162
+ 1982,
163
+ 2460,
164
+ 2627,
165
+ 3246,
166
+ 3253,
167
+ 3268,
168
+ 3536,
169
+ 3846,
170
+ 3961,
171
+ 4183,
172
+ 4667,
173
+ 6585,
174
+ 6647,
175
+ 7273,
176
+ 9061,
177
+ 9383,
178
+ 10428,
179
+ 10929,
180
+ 11938,
181
+ 12033,
182
+ 12331,
183
+ 12562,
184
+ 13793,
185
+ 14157,
186
+ 14635,
187
+ 15265,
188
+ 15618,
189
+ 16553,
190
+ 16604,
191
+ 18362,
192
+ 18956,
193
+ 20075,
194
+ 21675,
195
+ 22520,
196
+ 26130,
197
+ 26161,
198
+ 26435,
199
+ 28279,
200
+ 29464,
201
+ 31650,
202
+ 32302,
203
+ 32470,
204
+ 36865,
205
+ 42863,
206
+ 47425,
207
+ 49870,
208
+ 50254,
209
+ 50258,
210
+ 50358,
211
+ 50359,
212
+ 50360,
213
+ 50361,
214
+ 50362
215
+ ],
216
+ "task_to_id": {
217
+ "transcribe": 50359,
218
+ "translate": 50358
219
+ },
220
+ "transformers_version": "4.28.0",
221
+ "use_cache": false
222
+ }
preprocessor_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd3427ce93ebfd9db8477e7dcd4dba0373a35e12b8542b0974f8ef9bd88ad100
3
- size 134
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da16983c53d3105ee4975ba50a8f71a93de2cc8058a9452377c63d4aa87fae75
3
+ size 151098921
special_tokens_map.json CHANGED
@@ -22,7 +22,7 @@
22
  "<|hi|>",
23
  "<|fi|>",
24
  "<|vi|>",
25
- "<|iw|>",
26
  "<|uk|>",
27
  "<|el|>",
28
  "<|ms|>",
@@ -124,7 +124,7 @@
124
  },
125
  "pad_token": "<|endoftext|>",
126
  "unk_token": {
127
- "content": "",
128
  "lstrip": false,
129
  "normalized": true,
130
  "rstrip": false,
 
22
  "<|hi|>",
23
  "<|fi|>",
24
  "<|vi|>",
25
+ "<|he|>",
26
  "<|uk|>",
27
  "<|el|>",
28
  "<|ms|>",
 
124
  },
125
  "pad_token": "<|endoftext|>",
126
  "unk_token": {
127
+ "content": "<|endoftext|>",
128
  "lstrip": false,
129
  "normalized": true,
130
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -9,6 +9,7 @@
9
  "rstrip": false,
10
  "single_word": false
11
  },
 
12
  "eos_token": {
13
  "__type": "AddedToken",
14
  "content": "<|endoftext|>",
@@ -19,15 +20,13 @@
19
  },
20
  "errors": "replace",
21
  "model_max_length": 225,
22
- "name_or_path": "openai/whisper-tiny",
23
  "pad_token": null,
24
  "processor_class": "WhisperProcessor",
25
  "return_attention_mask": false,
26
- "special_tokens_map_file": null,
27
  "tokenizer_class": "WhisperTokenizer",
28
  "unk_token": {
29
  "__type": "AddedToken",
30
- "content": "",
31
  "lstrip": false,
32
  "normalized": true,
33
  "rstrip": false,
 
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
+ "clean_up_tokenization_spaces": true,
13
  "eos_token": {
14
  "__type": "AddedToken",
15
  "content": "<|endoftext|>",
 
20
  },
21
  "errors": "replace",
22
  "model_max_length": 225,
 
23
  "pad_token": null,
24
  "processor_class": "WhisperProcessor",
25
  "return_attention_mask": false,
 
26
  "tokenizer_class": "WhisperTokenizer",
27
  "unk_token": {
28
  "__type": "AddedToken",
29
+ "content": "<|endoftext|>",
30
  "lstrip": false,
31
  "normalized": true,
32
  "rstrip": false,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:171a03baa2c381e6034a7beba11edc139f49d6234a93c560002137ea32c65a3d
3
- size 129
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede4c88583703fa2db651acd3fbc33d94e8ebbf02952cdd59e3209fe5f529ad6
3
+ size 3771
vocab.json CHANGED
@@ -314,6 +314,7 @@
314
  ";;": 35746,
315
  "<": 27,
316
  "</": 3433,
 
317
  "=": 28,
318
  "=\"": 13114,
319
  "=\"#": 34106,
 
314
  ";;": 35746,
315
  "<": 27,
316
  "</": 3433,
317
+ "<|endoftext|>": 50257,
318
  "=": 28,
319
  "=\"": 13114,
320
  "=\"#": 34106,