AmirMohseni commited on
Commit
8e71aca
·
verified ·
1 Parent(s): 7e6a201

Upload quantized Persian Whisper model

Browse files
config.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 4
6
+ ],
7
+ [
8
+ 2,
9
+ 11
10
+ ],
11
+ [
12
+ 3,
13
+ 3
14
+ ],
15
+ [
16
+ 3,
17
+ 6
18
+ ],
19
+ [
20
+ 3,
21
+ 11
22
+ ],
23
+ [
24
+ 3,
25
+ 14
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
+ 50358
129
+ ],
130
+ "suppress_ids": [
131
+ 1,
132
+ 2,
133
+ 7,
134
+ 8,
135
+ 9,
136
+ 10,
137
+ 14,
138
+ 25,
139
+ 26,
140
+ 27,
141
+ 28,
142
+ 29,
143
+ 31,
144
+ 58,
145
+ 59,
146
+ 60,
147
+ 61,
148
+ 62,
149
+ 63,
150
+ 90,
151
+ 91,
152
+ 92,
153
+ 93,
154
+ 359,
155
+ 503,
156
+ 522,
157
+ 542,
158
+ 873,
159
+ 893,
160
+ 902,
161
+ 918,
162
+ 922,
163
+ 931,
164
+ 1350,
165
+ 1853,
166
+ 1982,
167
+ 2460,
168
+ 2627,
169
+ 3246,
170
+ 3253,
171
+ 3268,
172
+ 3536,
173
+ 3846,
174
+ 3961,
175
+ 4183,
176
+ 4667,
177
+ 6585,
178
+ 6647,
179
+ 7273,
180
+ 9061,
181
+ 9383,
182
+ 10428,
183
+ 10929,
184
+ 11938,
185
+ 12033,
186
+ 12331,
187
+ 12562,
188
+ 13793,
189
+ 14157,
190
+ 14635,
191
+ 15265,
192
+ 15618,
193
+ 16553,
194
+ 16604,
195
+ 18362,
196
+ 18956,
197
+ 20075,
198
+ 21675,
199
+ 22520,
200
+ 26130,
201
+ 26161,
202
+ 26435,
203
+ 28279,
204
+ 29464,
205
+ 31650,
206
+ 32302,
207
+ 32470,
208
+ 36865,
209
+ 42863,
210
+ 47425,
211
+ 49870,
212
+ 50254,
213
+ 50258,
214
+ 50359,
215
+ 50360,
216
+ 50361,
217
+ 50362,
218
+ 50363
219
+ ],
220
+ "suppress_ids_begin": [
221
+ 220,
222
+ 50257
223
+ ]
224
+ }
generation_config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 4
6
+ ],
7
+ [
8
+ 2,
9
+ 11
10
+ ],
11
+ [
12
+ 3,
13
+ 3
14
+ ],
15
+ [
16
+ 3,
17
+ 6
18
+ ],
19
+ [
20
+ 3,
21
+ 11
22
+ ],
23
+ [
24
+ 3,
25
+ 14
26
+ ]
27
+ ],
28
+ "begin_suppress_tokens": [
29
+ 220,
30
+ 50257
31
+ ],
32
+ "bos_token_id": 50257,
33
+ "decoder_start_token_id": 50258,
34
+ "eos_token_id": 50257,
35
+ "is_multilingual": true,
36
+ "lang_to_id": {
37
+ "<|af|>": 50327,
38
+ "<|am|>": 50334,
39
+ "<|ar|>": 50272,
40
+ "<|as|>": 50350,
41
+ "<|az|>": 50304,
42
+ "<|ba|>": 50355,
43
+ "<|be|>": 50330,
44
+ "<|bg|>": 50292,
45
+ "<|bn|>": 50302,
46
+ "<|bo|>": 50347,
47
+ "<|br|>": 50309,
48
+ "<|bs|>": 50315,
49
+ "<|ca|>": 50270,
50
+ "<|cs|>": 50283,
51
+ "<|cy|>": 50297,
52
+ "<|da|>": 50285,
53
+ "<|de|>": 50261,
54
+ "<|el|>": 50281,
55
+ "<|en|>": 50259,
56
+ "<|es|>": 50262,
57
+ "<|et|>": 50307,
58
+ "<|eu|>": 50310,
59
+ "<|fa|>": 50300,
60
+ "<|fi|>": 50277,
61
+ "<|fo|>": 50338,
62
+ "<|fr|>": 50265,
63
+ "<|gl|>": 50319,
64
+ "<|gu|>": 50333,
65
+ "<|haw|>": 50352,
66
+ "<|ha|>": 50354,
67
+ "<|he|>": 50279,
68
+ "<|hi|>": 50276,
69
+ "<|hr|>": 50291,
70
+ "<|ht|>": 50339,
71
+ "<|hu|>": 50286,
72
+ "<|hy|>": 50312,
73
+ "<|id|>": 50275,
74
+ "<|is|>": 50311,
75
+ "<|it|>": 50274,
76
+ "<|ja|>": 50266,
77
+ "<|jw|>": 50356,
78
+ "<|ka|>": 50329,
79
+ "<|kk|>": 50316,
80
+ "<|km|>": 50323,
81
+ "<|kn|>": 50306,
82
+ "<|ko|>": 50264,
83
+ "<|la|>": 50294,
84
+ "<|lb|>": 50345,
85
+ "<|ln|>": 50353,
86
+ "<|lo|>": 50336,
87
+ "<|lt|>": 50293,
88
+ "<|lv|>": 50301,
89
+ "<|mg|>": 50349,
90
+ "<|mi|>": 50295,
91
+ "<|mk|>": 50308,
92
+ "<|ml|>": 50296,
93
+ "<|mn|>": 50314,
94
+ "<|mr|>": 50320,
95
+ "<|ms|>": 50282,
96
+ "<|mt|>": 50343,
97
+ "<|my|>": 50346,
98
+ "<|ne|>": 50313,
99
+ "<|nl|>": 50271,
100
+ "<|nn|>": 50342,
101
+ "<|no|>": 50288,
102
+ "<|oc|>": 50328,
103
+ "<|pa|>": 50321,
104
+ "<|pl|>": 50269,
105
+ "<|ps|>": 50340,
106
+ "<|pt|>": 50267,
107
+ "<|ro|>": 50284,
108
+ "<|ru|>": 50263,
109
+ "<|sa|>": 50344,
110
+ "<|sd|>": 50332,
111
+ "<|si|>": 50322,
112
+ "<|sk|>": 50298,
113
+ "<|sl|>": 50305,
114
+ "<|sn|>": 50324,
115
+ "<|so|>": 50326,
116
+ "<|sq|>": 50317,
117
+ "<|sr|>": 50303,
118
+ "<|su|>": 50357,
119
+ "<|sv|>": 50273,
120
+ "<|sw|>": 50318,
121
+ "<|ta|>": 50287,
122
+ "<|te|>": 50299,
123
+ "<|tg|>": 50331,
124
+ "<|th|>": 50289,
125
+ "<|tk|>": 50341,
126
+ "<|tl|>": 50348,
127
+ "<|tr|>": 50268,
128
+ "<|tt|>": 50351,
129
+ "<|uk|>": 50280,
130
+ "<|ur|>": 50290,
131
+ "<|uz|>": 50337,
132
+ "<|vi|>": 50278,
133
+ "<|yi|>": 50335,
134
+ "<|yo|>": 50325,
135
+ "<|yue|>": 50358,
136
+ "<|zh|>": 50260
137
+ },
138
+ "language": "persian",
139
+ "max_initial_timestamp_index": 50,
140
+ "max_length": 448,
141
+ "no_timestamps_token_id": 50364,
142
+ "pad_token_id": 50257,
143
+ "prev_sot_token_id": 50362,
144
+ "return_timestamps": false,
145
+ "suppress_tokens": [
146
+ 1,
147
+ 2,
148
+ 7,
149
+ 8,
150
+ 9,
151
+ 10,
152
+ 14,
153
+ 25,
154
+ 26,
155
+ 27,
156
+ 28,
157
+ 29,
158
+ 31,
159
+ 58,
160
+ 59,
161
+ 60,
162
+ 61,
163
+ 62,
164
+ 63,
165
+ 90,
166
+ 91,
167
+ 92,
168
+ 93,
169
+ 359,
170
+ 503,
171
+ 522,
172
+ 542,
173
+ 873,
174
+ 893,
175
+ 902,
176
+ 918,
177
+ 922,
178
+ 931,
179
+ 1350,
180
+ 1853,
181
+ 1982,
182
+ 2460,
183
+ 2627,
184
+ 3246,
185
+ 3253,
186
+ 3268,
187
+ 3536,
188
+ 3846,
189
+ 3961,
190
+ 4183,
191
+ 4667,
192
+ 6585,
193
+ 6647,
194
+ 7273,
195
+ 9061,
196
+ 9383,
197
+ 10428,
198
+ 10929,
199
+ 11938,
200
+ 12033,
201
+ 12331,
202
+ 12562,
203
+ 13793,
204
+ 14157,
205
+ 14635,
206
+ 15265,
207
+ 15618,
208
+ 16553,
209
+ 16604,
210
+ 18362,
211
+ 18956,
212
+ 20075,
213
+ 21675,
214
+ 22520,
215
+ 26130,
216
+ 26161,
217
+ 26435,
218
+ 28279,
219
+ 29464,
220
+ 31650,
221
+ 32302,
222
+ 32470,
223
+ 36865,
224
+ 42863,
225
+ 47425,
226
+ 49870,
227
+ 50254,
228
+ 50258,
229
+ 50359,
230
+ 50360,
231
+ 50361,
232
+ 50362,
233
+ 50363
234
+ ],
235
+ "task": "transcribe",
236
+ "task_to_id": {
237
+ "transcribe": 50360,
238
+ "translate": 50359
239
+ },
240
+ "transformers_version": "4.48.0"
241
+ }
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb84937d374e11a96879f774404cb5c3d5e52b06b145aa9acd7a67c0d193991d
3
+ size 1551326177
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
vocabulary.json ADDED
The diff for this file is too large to render. See raw diff