hans00 commited on
Commit
bb74452
·
verified ·
1 Parent(s): ae4e2cc

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-small",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": [
10
+ 220,
11
+ 50257
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 50258,
20
+ "dropout": 0.0,
21
+ "encoder_attention_heads": 12,
22
+ "encoder_ffn_dim": 3072,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 12,
25
+ "eos_token_id": 50257,
26
+ "forced_decoder_ids": [
27
+ [
28
+ 1,
29
+ 50259
30
+ ],
31
+ [
32
+ 2,
33
+ 50359
34
+ ],
35
+ [
36
+ 3,
37
+ 50363
38
+ ]
39
+ ],
40
+ "init_std": 0.02,
41
+ "is_encoder_decoder": true,
42
+ "max_length": 448,
43
+ "max_source_positions": 1500,
44
+ "max_target_positions": 448,
45
+ "model_type": "whisper",
46
+ "num_hidden_layers": 12,
47
+ "num_mel_bins": 80,
48
+ "pad_token_id": 50257,
49
+ "scale_embedding": false,
50
+ "suppress_tokens": [
51
+ 1,
52
+ 2,
53
+ 7,
54
+ 8,
55
+ 9,
56
+ 10,
57
+ 14,
58
+ 25,
59
+ 26,
60
+ 27,
61
+ 28,
62
+ 29,
63
+ 31,
64
+ 58,
65
+ 59,
66
+ 60,
67
+ 61,
68
+ 62,
69
+ 63,
70
+ 90,
71
+ 91,
72
+ 92,
73
+ 93,
74
+ 359,
75
+ 503,
76
+ 522,
77
+ 542,
78
+ 873,
79
+ 893,
80
+ 902,
81
+ 918,
82
+ 922,
83
+ 931,
84
+ 1350,
85
+ 1853,
86
+ 1982,
87
+ 2460,
88
+ 2627,
89
+ 3246,
90
+ 3253,
91
+ 3268,
92
+ 3536,
93
+ 3846,
94
+ 3961,
95
+ 4183,
96
+ 4667,
97
+ 6585,
98
+ 6647,
99
+ 7273,
100
+ 9061,
101
+ 9383,
102
+ 10428,
103
+ 10929,
104
+ 11938,
105
+ 12033,
106
+ 12331,
107
+ 12562,
108
+ 13793,
109
+ 14157,
110
+ 14635,
111
+ 15265,
112
+ 15618,
113
+ 16553,
114
+ 16604,
115
+ 18362,
116
+ 18956,
117
+ 20075,
118
+ 21675,
119
+ 22520,
120
+ 26130,
121
+ 26161,
122
+ 26435,
123
+ 28279,
124
+ 29464,
125
+ 31650,
126
+ 32302,
127
+ 32470,
128
+ 36865,
129
+ 42863,
130
+ 47425,
131
+ 49870,
132
+ 50254,
133
+ 50258,
134
+ 50360,
135
+ 50361,
136
+ 50362
137
+ ],
138
+ "torch_dtype": "float32",
139
+ "transformers_version": "4.27.0.dev0",
140
+ "use_cache": true,
141
+ "vocab_size": 51865
142
+ }
generation_config.json ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "4.27.0.dev0"
221
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/decoder_model_merged_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944beba5a09f21b18a9856cdc42f98bba8641c01823ddb7dce77db4bc1925907
3
+ size 196598134
onnx/encoder_model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87ed5a8e6df837185feb613d74de58b068f178d85261dc2e64d1d5340cd95e7e
3
+ size 92574888
preprocessor_config.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1024,
22
+ "name_or_path": "openai/whisper-small",
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": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff