iamSamurai commited on
Commit
f52e5d4
·
verified ·
1 Parent(s): cdec3a5

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 13,
5
+ 15
6
+ ],
7
+ [
8
+ 15,
9
+ 4
10
+ ],
11
+ [
12
+ 15,
13
+ 15
14
+ ],
15
+ [
16
+ 16,
17
+ 1
18
+ ],
19
+ [
20
+ 20,
21
+ 0
22
+ ],
23
+ [
24
+ 23,
25
+ 4
26
+ ]
27
+ ],
28
+ "lang_ids": [
29
+ 50259,
30
+ 50260,
31
+ 50261,
32
+ 50262,
33
+ 50263,
34
+ 50264,
35
+ 50265,
36
+ 50266,
37
+ 50267,
38
+ 50268,
39
+ 50269,
40
+ 50270,
41
+ 50271,
42
+ 50272,
43
+ 50273,
44
+ 50274,
45
+ 50275,
46
+ 50276,
47
+ 50277,
48
+ 50278,
49
+ 50279,
50
+ 50280,
51
+ 50281,
52
+ 50282,
53
+ 50283,
54
+ 50284,
55
+ 50285,
56
+ 50286,
57
+ 50287,
58
+ 50288,
59
+ 50289,
60
+ 50290,
61
+ 50291,
62
+ 50292,
63
+ 50293,
64
+ 50294,
65
+ 50295,
66
+ 50296,
67
+ 50297,
68
+ 50298,
69
+ 50299,
70
+ 50300,
71
+ 50301,
72
+ 50302,
73
+ 50303,
74
+ 50304,
75
+ 50305,
76
+ 50306,
77
+ 50307,
78
+ 50308,
79
+ 50309,
80
+ 50310,
81
+ 50311,
82
+ 50312,
83
+ 50313,
84
+ 50314,
85
+ 50315,
86
+ 50316,
87
+ 50317,
88
+ 50318,
89
+ 50319,
90
+ 50320,
91
+ 50321,
92
+ 50322,
93
+ 50323,
94
+ 50324,
95
+ 50325,
96
+ 50326,
97
+ 50327,
98
+ 50328,
99
+ 50329,
100
+ 50330,
101
+ 50331,
102
+ 50332,
103
+ 50333,
104
+ 50334,
105
+ 50335,
106
+ 50336,
107
+ 50337,
108
+ 50338,
109
+ 50339,
110
+ 50340,
111
+ 50341,
112
+ 50342,
113
+ 50343,
114
+ 50344,
115
+ 50345,
116
+ 50346,
117
+ 50347,
118
+ 50348,
119
+ 50349,
120
+ 50350,
121
+ 50351,
122
+ 50352,
123
+ 50353,
124
+ 50354,
125
+ 50355,
126
+ 50356,
127
+ 50357
128
+ ],
129
+ "suppress_ids": [
130
+ 1,
131
+ 2,
132
+ 7,
133
+ 8,
134
+ 9,
135
+ 10,
136
+ 14,
137
+ 25,
138
+ 26,
139
+ 27,
140
+ 28,
141
+ 29,
142
+ 31,
143
+ 58,
144
+ 59,
145
+ 60,
146
+ 61,
147
+ 62,
148
+ 63,
149
+ 90,
150
+ 91,
151
+ 92,
152
+ 93,
153
+ 359,
154
+ 503,
155
+ 522,
156
+ 542,
157
+ 873,
158
+ 893,
159
+ 902,
160
+ 918,
161
+ 922,
162
+ 931,
163
+ 1350,
164
+ 1853,
165
+ 1982,
166
+ 2460,
167
+ 2627,
168
+ 3246,
169
+ 3253,
170
+ 3268,
171
+ 3536,
172
+ 3846,
173
+ 3961,
174
+ 4183,
175
+ 4667,
176
+ 6585,
177
+ 6647,
178
+ 7273,
179
+ 9061,
180
+ 9383,
181
+ 10428,
182
+ 10929,
183
+ 11938,
184
+ 12033,
185
+ 12331,
186
+ 12562,
187
+ 13793,
188
+ 14157,
189
+ 14635,
190
+ 15265,
191
+ 15618,
192
+ 16553,
193
+ 16604,
194
+ 18362,
195
+ 18956,
196
+ 20075,
197
+ 21675,
198
+ 22520,
199
+ 26130,
200
+ 26161,
201
+ 26435,
202
+ 28279,
203
+ 29464,
204
+ 31650,
205
+ 32302,
206
+ 32470,
207
+ 36865,
208
+ 42863,
209
+ 47425,
210
+ 49870,
211
+ 50254,
212
+ 50258,
213
+ 50358,
214
+ 50359,
215
+ 50360,
216
+ 50361,
217
+ 50362
218
+ ],
219
+ "suppress_ids_begin": [
220
+ 220,
221
+ 50257
222
+ ]
223
+ }
generation_config.json ADDED
@@ -0,0 +1,283 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 13,
5
+ 15
6
+ ],
7
+ [
8
+ 15,
9
+ 4
10
+ ],
11
+ [
12
+ 15,
13
+ 15
14
+ ],
15
+ [
16
+ 16,
17
+ 1
18
+ ],
19
+ [
20
+ 20,
21
+ 0
22
+ ],
23
+ [
24
+ 23,
25
+ 4
26
+ ]
27
+ ],
28
+ "assistant_confidence_threshold": 0.4,
29
+ "assistant_lookbehind": 10,
30
+ "begin_suppress_tokens": [
31
+ 220,
32
+ 50257
33
+ ],
34
+ "bos_token_id": 50257,
35
+ "decoder_start_token_id": 50258,
36
+ "diversity_penalty": 0.0,
37
+ "do_sample": false,
38
+ "early_stopping": false,
39
+ "encoder_no_repeat_ngram_size": 0,
40
+ "encoder_repetition_penalty": 1.0,
41
+ "eos_token_id": [
42
+ 50257
43
+ ],
44
+ "epsilon_cutoff": 0.0,
45
+ "eta_cutoff": 0.0,
46
+ "forced_decoder_ids": [
47
+ [
48
+ 1,
49
+ 50259
50
+ ],
51
+ [
52
+ 2,
53
+ 50359
54
+ ],
55
+ [
56
+ 3,
57
+ 50363
58
+ ]
59
+ ],
60
+ "is_multilingual": true,
61
+ "lang_to_id": {
62
+ "<|af|>": 50327,
63
+ "<|am|>": 50334,
64
+ "<|ar|>": 50272,
65
+ "<|as|>": 50350,
66
+ "<|az|>": 50304,
67
+ "<|ba|>": 50355,
68
+ "<|be|>": 50330,
69
+ "<|bg|>": 50292,
70
+ "<|bn|>": 50302,
71
+ "<|bo|>": 50347,
72
+ "<|br|>": 50309,
73
+ "<|bs|>": 50315,
74
+ "<|ca|>": 50270,
75
+ "<|cs|>": 50283,
76
+ "<|cy|>": 50297,
77
+ "<|da|>": 50285,
78
+ "<|de|>": 50261,
79
+ "<|el|>": 50281,
80
+ "<|en|>": 50259,
81
+ "<|es|>": 50262,
82
+ "<|et|>": 50307,
83
+ "<|eu|>": 50310,
84
+ "<|fa|>": 50300,
85
+ "<|fi|>": 50277,
86
+ "<|fo|>": 50338,
87
+ "<|fr|>": 50265,
88
+ "<|gl|>": 50319,
89
+ "<|gu|>": 50333,
90
+ "<|haw|>": 50352,
91
+ "<|ha|>": 50354,
92
+ "<|he|>": 50279,
93
+ "<|hi|>": 50276,
94
+ "<|hr|>": 50291,
95
+ "<|ht|>": 50339,
96
+ "<|hu|>": 50286,
97
+ "<|hy|>": 50312,
98
+ "<|id|>": 50275,
99
+ "<|is|>": 50311,
100
+ "<|it|>": 50274,
101
+ "<|ja|>": 50266,
102
+ "<|jw|>": 50356,
103
+ "<|ka|>": 50329,
104
+ "<|kk|>": 50316,
105
+ "<|km|>": 50323,
106
+ "<|kn|>": 50306,
107
+ "<|ko|>": 50264,
108
+ "<|la|>": 50294,
109
+ "<|lb|>": 50345,
110
+ "<|ln|>": 50353,
111
+ "<|lo|>": 50336,
112
+ "<|lt|>": 50293,
113
+ "<|lv|>": 50301,
114
+ "<|mg|>": 50349,
115
+ "<|mi|>": 50295,
116
+ "<|mk|>": 50308,
117
+ "<|ml|>": 50296,
118
+ "<|mn|>": 50314,
119
+ "<|mr|>": 50320,
120
+ "<|ms|>": 50282,
121
+ "<|mt|>": 50343,
122
+ "<|my|>": 50346,
123
+ "<|ne|>": 50313,
124
+ "<|nl|>": 50271,
125
+ "<|nn|>": 50342,
126
+ "<|no|>": 50288,
127
+ "<|oc|>": 50328,
128
+ "<|pa|>": 50321,
129
+ "<|pl|>": 50269,
130
+ "<|ps|>": 50340,
131
+ "<|pt|>": 50267,
132
+ "<|ro|>": 50284,
133
+ "<|ru|>": 50263,
134
+ "<|sa|>": 50344,
135
+ "<|sd|>": 50332,
136
+ "<|si|>": 50322,
137
+ "<|sk|>": 50298,
138
+ "<|sl|>": 50305,
139
+ "<|sn|>": 50324,
140
+ "<|so|>": 50326,
141
+ "<|sq|>": 50317,
142
+ "<|sr|>": 50303,
143
+ "<|su|>": 50357,
144
+ "<|sv|>": 50273,
145
+ "<|sw|>": 50318,
146
+ "<|ta|>": 50287,
147
+ "<|te|>": 50299,
148
+ "<|tg|>": 50331,
149
+ "<|th|>": 50289,
150
+ "<|tk|>": 50341,
151
+ "<|tl|>": 50348,
152
+ "<|tr|>": 50268,
153
+ "<|tt|>": 50351,
154
+ "<|uk|>": 50280,
155
+ "<|ur|>": 50290,
156
+ "<|uz|>": 50337,
157
+ "<|vi|>": 50278,
158
+ "<|yi|>": 50335,
159
+ "<|yo|>": 50325,
160
+ "<|zh|>": 50260
161
+ },
162
+ "language": "english",
163
+ "length_penalty": 1.0,
164
+ "max_initial_timestamp_index": 50,
165
+ "max_length": 448,
166
+ "min_length": 0,
167
+ "no_repeat_ngram_size": 0,
168
+ "no_timestamps_token_id": 50363,
169
+ "num_assistant_tokens": 20,
170
+ "num_assistant_tokens_schedule": "constant",
171
+ "num_beam_groups": 1,
172
+ "num_beams": 1,
173
+ "num_return_sequences": 1,
174
+ "output_scores": false,
175
+ "pad_token_id": 50257,
176
+ "prev_sot_token_id": 50361,
177
+ "remove_invalid_values": false,
178
+ "repetition_penalty": 1.0,
179
+ "return_dict_in_generate": false,
180
+ "return_timestamps": false,
181
+ "suppress_tokens": [
182
+ 1,
183
+ 2,
184
+ 7,
185
+ 8,
186
+ 9,
187
+ 10,
188
+ 14,
189
+ 25,
190
+ 26,
191
+ 27,
192
+ 28,
193
+ 29,
194
+ 31,
195
+ 58,
196
+ 59,
197
+ 60,
198
+ 61,
199
+ 62,
200
+ 63,
201
+ 90,
202
+ 91,
203
+ 92,
204
+ 93,
205
+ 359,
206
+ 503,
207
+ 522,
208
+ 542,
209
+ 873,
210
+ 893,
211
+ 902,
212
+ 918,
213
+ 922,
214
+ 931,
215
+ 1350,
216
+ 1853,
217
+ 1982,
218
+ 2460,
219
+ 2627,
220
+ 3246,
221
+ 3253,
222
+ 3268,
223
+ 3536,
224
+ 3846,
225
+ 3961,
226
+ 4183,
227
+ 4667,
228
+ 6585,
229
+ 6647,
230
+ 7273,
231
+ 9061,
232
+ 9383,
233
+ 10428,
234
+ 10929,
235
+ 11938,
236
+ 12033,
237
+ 12331,
238
+ 12562,
239
+ 13793,
240
+ 14157,
241
+ 14635,
242
+ 15265,
243
+ 15618,
244
+ 16553,
245
+ 16604,
246
+ 18362,
247
+ 18956,
248
+ 20075,
249
+ 21675,
250
+ 22520,
251
+ 26130,
252
+ 26161,
253
+ 26435,
254
+ 28279,
255
+ 29464,
256
+ 31650,
257
+ 32302,
258
+ 32470,
259
+ 36865,
260
+ 42863,
261
+ 47425,
262
+ 49870,
263
+ 50254,
264
+ 50258,
265
+ 50358,
266
+ 50359,
267
+ 50360,
268
+ 50361,
269
+ 50362
270
+ ],
271
+ "target_lookbehind": 10,
272
+ "task": "transcribe",
273
+ "task_to_id": {
274
+ "transcribe": 50359,
275
+ "translate": 50358
276
+ },
277
+ "temperature": 1.0,
278
+ "top_k": 50,
279
+ "top_p": 1.0,
280
+ "transformers_version": "5.5.0",
281
+ "typical_p": 1.0,
282
+ "use_cache": false
283
+ }
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9328f0e774d410e06e4d56c123fab6dd0f21198258f6a4193552be28988abcca
3
+ size 1527906453
processor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "chunk_length": 30,
4
+ "dither": 0.0,
5
+ "feature_extractor_type": "WhisperFeatureExtractor",
6
+ "feature_size": 80,
7
+ "hop_length": 160,
8
+ "n_fft": 400,
9
+ "n_samples": 480000,
10
+ "nb_max_frames": 3000,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "return_attention_mask": false,
14
+ "sampling_rate": 16000
15
+ },
16
+ "processor_class": "WhisperProcessor"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": {
9
+ "<|endoftext|>": "<|endoftext|>",
10
+ "<|startoftranscript|>": "<|startoftranscript|>",
11
+ "<|en|>": "<|en|>",
12
+ "<|zh|>": "<|zh|>",
13
+ "<|de|>": "<|de|>",
14
+ "<|es|>": "<|es|>",
15
+ "<|ru|>": "<|ru|>",
16
+ "<|ko|>": "<|ko|>",
17
+ "<|fr|>": "<|fr|>",
18
+ "<|ja|>": "<|ja|>",
19
+ "<|pt|>": "<|pt|>",
20
+ "<|tr|>": "<|tr|>",
21
+ "<|pl|>": "<|pl|>",
22
+ "<|ca|>": "<|ca|>",
23
+ "<|nl|>": "<|nl|>",
24
+ "<|ar|>": "<|ar|>",
25
+ "<|sv|>": "<|sv|>",
26
+ "<|it|>": "<|it|>",
27
+ "<|id|>": "<|id|>",
28
+ "<|hi|>": "<|hi|>",
29
+ "<|fi|>": "<|fi|>",
30
+ "<|vi|>": "<|vi|>",
31
+ "<|he|>": "<|he|>",
32
+ "<|uk|>": "<|uk|>",
33
+ "<|el|>": "<|el|>",
34
+ "<|ms|>": "<|ms|>",
35
+ "<|cs|>": "<|cs|>",
36
+ "<|ro|>": "<|ro|>",
37
+ "<|da|>": "<|da|>",
38
+ "<|hu|>": "<|hu|>",
39
+ "<|ta|>": "<|ta|>",
40
+ "<|no|>": "<|no|>",
41
+ "<|th|>": "<|th|>",
42
+ "<|ur|>": "<|ur|>",
43
+ "<|hr|>": "<|hr|>",
44
+ "<|bg|>": "<|bg|>",
45
+ "<|lt|>": "<|lt|>",
46
+ "<|la|>": "<|la|>",
47
+ "<|mi|>": "<|mi|>",
48
+ "<|ml|>": "<|ml|>",
49
+ "<|cy|>": "<|cy|>",
50
+ "<|sk|>": "<|sk|>",
51
+ "<|te|>": "<|te|>",
52
+ "<|fa|>": "<|fa|>",
53
+ "<|lv|>": "<|lv|>",
54
+ "<|bn|>": "<|bn|>",
55
+ "<|sr|>": "<|sr|>",
56
+ "<|az|>": "<|az|>",
57
+ "<|sl|>": "<|sl|>",
58
+ "<|kn|>": "<|kn|>",
59
+ "<|et|>": "<|et|>",
60
+ "<|mk|>": "<|mk|>",
61
+ "<|br|>": "<|br|>",
62
+ "<|eu|>": "<|eu|>",
63
+ "<|is|>": "<|is|>",
64
+ "<|hy|>": "<|hy|>",
65
+ "<|ne|>": "<|ne|>",
66
+ "<|mn|>": "<|mn|>",
67
+ "<|bs|>": "<|bs|>",
68
+ "<|kk|>": "<|kk|>",
69
+ "<|sq|>": "<|sq|>",
70
+ "<|sw|>": "<|sw|>",
71
+ "<|gl|>": "<|gl|>",
72
+ "<|mr|>": "<|mr|>",
73
+ "<|pa|>": "<|pa|>",
74
+ "<|si|>": "<|si|>",
75
+ "<|km|>": "<|km|>",
76
+ "<|sn|>": "<|sn|>",
77
+ "<|yo|>": "<|yo|>",
78
+ "<|so|>": "<|so|>",
79
+ "<|af|>": "<|af|>",
80
+ "<|oc|>": "<|oc|>",
81
+ "<|ka|>": "<|ka|>",
82
+ "<|be|>": "<|be|>",
83
+ "<|tg|>": "<|tg|>",
84
+ "<|sd|>": "<|sd|>",
85
+ "<|gu|>": "<|gu|>",
86
+ "<|am|>": "<|am|>",
87
+ "<|yi|>": "<|yi|>",
88
+ "<|lo|>": "<|lo|>",
89
+ "<|uz|>": "<|uz|>",
90
+ "<|fo|>": "<|fo|>",
91
+ "<|ht|>": "<|ht|>",
92
+ "<|ps|>": "<|ps|>",
93
+ "<|tk|>": "<|tk|>",
94
+ "<|nn|>": "<|nn|>",
95
+ "<|mt|>": "<|mt|>",
96
+ "<|sa|>": "<|sa|>",
97
+ "<|lb|>": "<|lb|>",
98
+ "<|my|>": "<|my|>",
99
+ "<|bo|>": "<|bo|>",
100
+ "<|tl|>": "<|tl|>",
101
+ "<|mg|>": "<|mg|>",
102
+ "<|as|>": "<|as|>",
103
+ "<|tt|>": "<|tt|>",
104
+ "<|haw|>": "<|haw|>",
105
+ "<|ln|>": "<|ln|>",
106
+ "<|ha|>": "<|ha|>",
107
+ "<|ba|>": "<|ba|>",
108
+ "<|jw|>": "<|jw|>",
109
+ "<|su|>": "<|su|>",
110
+ "<|translate|>": "<|translate|>",
111
+ "<|transcribe|>": "<|transcribe|>",
112
+ "<|startoflm|>": "<|startoflm|>",
113
+ "<|startofprev|>": "<|startofprev|>",
114
+ "<|nocaptions|>": "<|nocaptions|>",
115
+ "<|notimestamps|>": "<|notimestamps|>"
116
+ },
117
+ "is_local": true,
118
+ "language": "english",
119
+ "model_max_length": 1024,
120
+ "pad_token": "<|endoftext|>",
121
+ "predict_timestamps": false,
122
+ "processor_class": "WhisperProcessor",
123
+ "return_attention_mask": false,
124
+ "task": "transcribe",
125
+ "tokenizer_class": "WhisperTokenizer",
126
+ "unk_token": "<|endoftext|>"
127
+ }
vocabulary.json ADDED
The diff for this file is too large to render. See raw diff