raghadOmar commited on
Commit
8f7276f
·
verified ·
1 Parent(s): 0845577

Upload processor

Browse files
added_tokens.json CHANGED
@@ -1,108 +1,109 @@
1
- {
2
- "<|af|>": 50327,
3
- "<|am|>": 50334,
4
- "<|ar|>": 50272,
5
- "<|as|>": 50350,
6
- "<|az|>": 50304,
7
- "<|ba|>": 50355,
8
- "<|be|>": 50330,
9
- "<|bg|>": 50292,
10
- "<|bn|>": 50302,
11
- "<|bo|>": 50347,
12
- "<|br|>": 50309,
13
- "<|bs|>": 50315,
14
- "<|ca|>": 50270,
15
- "<|cs|>": 50283,
16
- "<|cy|>": 50297,
17
- "<|da|>": 50285,
18
- "<|de|>": 50261,
19
- "<|el|>": 50281,
20
- "<|en|>": 50259,
21
- "<|es|>": 50262,
22
- "<|et|>": 50307,
23
- "<|eu|>": 50310,
24
- "<|fa|>": 50300,
25
- "<|fi|>": 50277,
26
- "<|fo|>": 50338,
27
- "<|fr|>": 50265,
28
- "<|gl|>": 50319,
29
- "<|gu|>": 50333,
30
- "<|haw|>": 50352,
31
- "<|ha|>": 50354,
32
- "<|he|>": 50279,
33
- "<|hi|>": 50276,
34
- "<|hr|>": 50291,
35
- "<|ht|>": 50339,
36
- "<|hu|>": 50286,
37
- "<|hy|>": 50312,
38
- "<|id|>": 50275,
39
- "<|is|>": 50311,
40
- "<|it|>": 50274,
41
- "<|ja|>": 50266,
42
- "<|jw|>": 50356,
43
- "<|ka|>": 50329,
44
- "<|kk|>": 50316,
45
- "<|km|>": 50323,
46
- "<|kn|>": 50306,
47
- "<|ko|>": 50264,
48
- "<|la|>": 50294,
49
- "<|lb|>": 50345,
50
- "<|ln|>": 50353,
51
- "<|lo|>": 50336,
52
- "<|lt|>": 50293,
53
- "<|lv|>": 50301,
54
- "<|mg|>": 50349,
55
- "<|mi|>": 50295,
56
- "<|mk|>": 50308,
57
- "<|ml|>": 50296,
58
- "<|mn|>": 50314,
59
- "<|mr|>": 50320,
60
- "<|ms|>": 50282,
61
- "<|mt|>": 50343,
62
- "<|my|>": 50346,
63
- "<|ne|>": 50313,
64
- "<|nl|>": 50271,
65
- "<|nn|>": 50342,
66
- "<|nocaptions|>": 50362,
67
- "<|notimestamps|>": 50363,
68
- "<|no|>": 50288,
69
- "<|oc|>": 50328,
70
- "<|pa|>": 50321,
71
- "<|pl|>": 50269,
72
- "<|ps|>": 50340,
73
- "<|pt|>": 50267,
74
- "<|ro|>": 50284,
75
- "<|ru|>": 50263,
76
- "<|sa|>": 50344,
77
- "<|sd|>": 50332,
78
- "<|si|>": 50322,
79
- "<|sk|>": 50298,
80
- "<|sl|>": 50305,
81
- "<|sn|>": 50324,
82
- "<|so|>": 50326,
83
- "<|sq|>": 50317,
84
- "<|sr|>": 50303,
85
- "<|startoflm|>": 50360,
86
- "<|startofprev|>": 50361,
87
- "<|startoftranscript|>": 50258,
88
- "<|su|>": 50357,
89
- "<|sv|>": 50273,
90
- "<|sw|>": 50318,
91
- "<|ta|>": 50287,
92
- "<|te|>": 50299,
93
- "<|tg|>": 50331,
94
- "<|th|>": 50289,
95
- "<|tk|>": 50341,
96
- "<|tl|>": 50348,
97
- "<|transcribe|>": 50359,
98
- "<|translate|>": 50358,
99
- "<|tr|>": 50268,
100
- "<|tt|>": 50351,
101
- "<|uk|>": 50280,
102
- "<|ur|>": 50290,
103
- "<|uz|>": 50337,
104
- "<|vi|>": 50278,
105
- "<|yi|>": 50335,
106
- "<|yo|>": 50325,
107
- "<|zh|>": 50260
108
- }
 
 
1
+ {
2
+ "<|af|>": 50327,
3
+ "<|am|>": 50334,
4
+ "<|ar|>": 50272,
5
+ "<|as|>": 50350,
6
+ "<|az|>": 50304,
7
+ "<|ba|>": 50355,
8
+ "<|be|>": 50330,
9
+ "<|bg|>": 50292,
10
+ "<|bn|>": 50302,
11
+ "<|bo|>": 50347,
12
+ "<|br|>": 50309,
13
+ "<|bs|>": 50315,
14
+ "<|ca|>": 50270,
15
+ "<|cs|>": 50283,
16
+ "<|cy|>": 50297,
17
+ "<|da|>": 50285,
18
+ "<|de|>": 50261,
19
+ "<|el|>": 50281,
20
+ "<|endoftext|>": 50257,
21
+ "<|en|>": 50259,
22
+ "<|es|>": 50262,
23
+ "<|et|>": 50307,
24
+ "<|eu|>": 50310,
25
+ "<|fa|>": 50300,
26
+ "<|fi|>": 50277,
27
+ "<|fo|>": 50338,
28
+ "<|fr|>": 50265,
29
+ "<|gl|>": 50319,
30
+ "<|gu|>": 50333,
31
+ "<|haw|>": 50352,
32
+ "<|ha|>": 50354,
33
+ "<|hi|>": 50276,
34
+ "<|hr|>": 50291,
35
+ "<|ht|>": 50339,
36
+ "<|hu|>": 50286,
37
+ "<|hy|>": 50312,
38
+ "<|id|>": 50275,
39
+ "<|is|>": 50311,
40
+ "<|it|>": 50274,
41
+ "<|iw|>": 50279,
42
+ "<|ja|>": 50266,
43
+ "<|jw|>": 50356,
44
+ "<|ka|>": 50329,
45
+ "<|kk|>": 50316,
46
+ "<|km|>": 50323,
47
+ "<|kn|>": 50306,
48
+ "<|ko|>": 50264,
49
+ "<|la|>": 50294,
50
+ "<|lb|>": 50345,
51
+ "<|ln|>": 50353,
52
+ "<|lo|>": 50336,
53
+ "<|lt|>": 50293,
54
+ "<|lv|>": 50301,
55
+ "<|mg|>": 50349,
56
+ "<|mi|>": 50295,
57
+ "<|mk|>": 50308,
58
+ "<|ml|>": 50296,
59
+ "<|mn|>": 50314,
60
+ "<|mr|>": 50320,
61
+ "<|ms|>": 50282,
62
+ "<|mt|>": 50343,
63
+ "<|my|>": 50346,
64
+ "<|ne|>": 50313,
65
+ "<|nl|>": 50271,
66
+ "<|nn|>": 50342,
67
+ "<|nocaptions|>": 50362,
68
+ "<|notimestamps|>": 50363,
69
+ "<|no|>": 50288,
70
+ "<|oc|>": 50328,
71
+ "<|pa|>": 50321,
72
+ "<|pl|>": 50269,
73
+ "<|ps|>": 50340,
74
+ "<|pt|>": 50267,
75
+ "<|ro|>": 50284,
76
+ "<|ru|>": 50263,
77
+ "<|sa|>": 50344,
78
+ "<|sd|>": 50332,
79
+ "<|si|>": 50322,
80
+ "<|sk|>": 50298,
81
+ "<|sl|>": 50305,
82
+ "<|sn|>": 50324,
83
+ "<|so|>": 50326,
84
+ "<|sq|>": 50317,
85
+ "<|sr|>": 50303,
86
+ "<|startoflm|>": 50360,
87
+ "<|startofprev|>": 50361,
88
+ "<|startoftranscript|>": 50258,
89
+ "<|su|>": 50357,
90
+ "<|sv|>": 50273,
91
+ "<|sw|>": 50318,
92
+ "<|ta|>": 50287,
93
+ "<|te|>": 50299,
94
+ "<|tg|>": 50331,
95
+ "<|th|>": 50289,
96
+ "<|tk|>": 50341,
97
+ "<|tl|>": 50348,
98
+ "<|transcribe|>": 50359,
99
+ "<|translate|>": 50358,
100
+ "<|tr|>": 50268,
101
+ "<|tt|>": 50351,
102
+ "<|uk|>": 50280,
103
+ "<|ur|>": 50290,
104
+ "<|uz|>": 50337,
105
+ "<|vi|>": 50278,
106
+ "<|yi|>": 50335,
107
+ "<|yo|>": 50325,
108
+ "<|zh|>": 50260
109
+ }
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
normalizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json CHANGED
@@ -1,14 +1,14 @@
1
- {
2
- "chunk_length": 30,
3
- "feature_extractor_type": "WhisperFeatureExtractor",
4
- "feature_size": 80,
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
- }
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
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
+ }
special_tokens_map.json CHANGED
@@ -1,139 +1,139 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|endoftext|>",
4
- "<|startoftranscript|>",
5
- "<|en|>",
6
- "<|zh|>",
7
- "<|de|>",
8
- "<|es|>",
9
- "<|ru|>",
10
- "<|ko|>",
11
- "<|fr|>",
12
- "<|ja|>",
13
- "<|pt|>",
14
- "<|tr|>",
15
- "<|pl|>",
16
- "<|ca|>",
17
- "<|nl|>",
18
- "<|ar|>",
19
- "<|sv|>",
20
- "<|it|>",
21
- "<|id|>",
22
- "<|hi|>",
23
- "<|fi|>",
24
- "<|vi|>",
25
- "<|he|>",
26
- "<|uk|>",
27
- "<|el|>",
28
- "<|ms|>",
29
- "<|cs|>",
30
- "<|ro|>",
31
- "<|da|>",
32
- "<|hu|>",
33
- "<|ta|>",
34
- "<|no|>",
35
- "<|th|>",
36
- "<|ur|>",
37
- "<|hr|>",
38
- "<|bg|>",
39
- "<|lt|>",
40
- "<|la|>",
41
- "<|mi|>",
42
- "<|ml|>",
43
- "<|cy|>",
44
- "<|sk|>",
45
- "<|te|>",
46
- "<|fa|>",
47
- "<|lv|>",
48
- "<|bn|>",
49
- "<|sr|>",
50
- "<|az|>",
51
- "<|sl|>",
52
- "<|kn|>",
53
- "<|et|>",
54
- "<|mk|>",
55
- "<|br|>",
56
- "<|eu|>",
57
- "<|is|>",
58
- "<|hy|>",
59
- "<|ne|>",
60
- "<|mn|>",
61
- "<|bs|>",
62
- "<|kk|>",
63
- "<|sq|>",
64
- "<|sw|>",
65
- "<|gl|>",
66
- "<|mr|>",
67
- "<|pa|>",
68
- "<|si|>",
69
- "<|km|>",
70
- "<|sn|>",
71
- "<|yo|>",
72
- "<|so|>",
73
- "<|af|>",
74
- "<|oc|>",
75
- "<|ka|>",
76
- "<|be|>",
77
- "<|tg|>",
78
- "<|sd|>",
79
- "<|gu|>",
80
- "<|am|>",
81
- "<|yi|>",
82
- "<|lo|>",
83
- "<|uz|>",
84
- "<|fo|>",
85
- "<|ht|>",
86
- "<|ps|>",
87
- "<|tk|>",
88
- "<|nn|>",
89
- "<|mt|>",
90
- "<|sa|>",
91
- "<|lb|>",
92
- "<|my|>",
93
- "<|bo|>",
94
- "<|tl|>",
95
- "<|mg|>",
96
- "<|as|>",
97
- "<|tt|>",
98
- "<|haw|>",
99
- "<|ln|>",
100
- "<|ha|>",
101
- "<|ba|>",
102
- "<|jw|>",
103
- "<|su|>",
104
- "<|translate|>",
105
- "<|transcribe|>",
106
- "<|startoflm|>",
107
- "<|startofprev|>",
108
- "<|nocaptions|>",
109
- "<|notimestamps|>"
110
- ],
111
- "bos_token": {
112
- "content": "<|endoftext|>",
113
- "lstrip": false,
114
- "normalized": true,
115
- "rstrip": false,
116
- "single_word": false
117
- },
118
- "eos_token": {
119
- "content": "<|endoftext|>",
120
- "lstrip": false,
121
- "normalized": true,
122
- "rstrip": false,
123
- "single_word": false
124
- },
125
- "pad_token": {
126
- "content": "<|endoftext|>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false
131
- },
132
- "unk_token": {
133
- "content": "<|endoftext|>",
134
- "lstrip": false,
135
- "normalized": true,
136
- "rstrip": false,
137
- "single_word": false
138
- }
139
- }
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|startoftranscript|>",
5
+ "<|en|>",
6
+ "<|zh|>",
7
+ "<|de|>",
8
+ "<|es|>",
9
+ "<|ru|>",
10
+ "<|ko|>",
11
+ "<|fr|>",
12
+ "<|ja|>",
13
+ "<|pt|>",
14
+ "<|tr|>",
15
+ "<|pl|>",
16
+ "<|ca|>",
17
+ "<|nl|>",
18
+ "<|ar|>",
19
+ "<|sv|>",
20
+ "<|it|>",
21
+ "<|id|>",
22
+ "<|hi|>",
23
+ "<|fi|>",
24
+ "<|vi|>",
25
+ "<|iw|>",
26
+ "<|uk|>",
27
+ "<|el|>",
28
+ "<|ms|>",
29
+ "<|cs|>",
30
+ "<|ro|>",
31
+ "<|da|>",
32
+ "<|hu|>",
33
+ "<|ta|>",
34
+ "<|no|>",
35
+ "<|th|>",
36
+ "<|ur|>",
37
+ "<|hr|>",
38
+ "<|bg|>",
39
+ "<|lt|>",
40
+ "<|la|>",
41
+ "<|mi|>",
42
+ "<|ml|>",
43
+ "<|cy|>",
44
+ "<|sk|>",
45
+ "<|te|>",
46
+ "<|fa|>",
47
+ "<|lv|>",
48
+ "<|bn|>",
49
+ "<|sr|>",
50
+ "<|az|>",
51
+ "<|sl|>",
52
+ "<|kn|>",
53
+ "<|et|>",
54
+ "<|mk|>",
55
+ "<|br|>",
56
+ "<|eu|>",
57
+ "<|is|>",
58
+ "<|hy|>",
59
+ "<|ne|>",
60
+ "<|mn|>",
61
+ "<|bs|>",
62
+ "<|kk|>",
63
+ "<|sq|>",
64
+ "<|sw|>",
65
+ "<|gl|>",
66
+ "<|mr|>",
67
+ "<|pa|>",
68
+ "<|si|>",
69
+ "<|km|>",
70
+ "<|sn|>",
71
+ "<|yo|>",
72
+ "<|so|>",
73
+ "<|af|>",
74
+ "<|oc|>",
75
+ "<|ka|>",
76
+ "<|be|>",
77
+ "<|tg|>",
78
+ "<|sd|>",
79
+ "<|gu|>",
80
+ "<|am|>",
81
+ "<|yi|>",
82
+ "<|lo|>",
83
+ "<|uz|>",
84
+ "<|fo|>",
85
+ "<|ht|>",
86
+ "<|ps|>",
87
+ "<|tk|>",
88
+ "<|nn|>",
89
+ "<|mt|>",
90
+ "<|sa|>",
91
+ "<|lb|>",
92
+ "<|my|>",
93
+ "<|bo|>",
94
+ "<|tl|>",
95
+ "<|mg|>",
96
+ "<|as|>",
97
+ "<|tt|>",
98
+ "<|haw|>",
99
+ "<|ln|>",
100
+ "<|ha|>",
101
+ "<|ba|>",
102
+ "<|jw|>",
103
+ "<|su|>",
104
+ "<|translate|>",
105
+ "<|transcribe|>",
106
+ "<|startoflm|>",
107
+ "<|startofprev|>",
108
+ "<|nocaptions|>",
109
+ "<|notimestamps|>"
110
+ ],
111
+ "bos_token": {
112
+ "content": "<|endoftext|>",
113
+ "lstrip": false,
114
+ "normalized": true,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "eos_token": {
119
+ "content": "<|endoftext|>",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "pad_token": {
126
+ "content": "<|endoftext|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false
131
+ },
132
+ "unk_token": {
133
+ "content": "",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false
138
+ }
139
+ }
tokenizer_config.json CHANGED
@@ -1,981 +1,981 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "50257": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "50258": {
14
- "content": "<|startoftranscript|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "50259": {
22
- "content": "<|en|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "50260": {
30
- "content": "<|zh|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "50261": {
38
- "content": "<|de|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "50262": {
46
- "content": "<|es|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "50263": {
54
- "content": "<|ru|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "50264": {
62
- "content": "<|ko|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "50265": {
70
- "content": "<|fr|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "50266": {
78
- "content": "<|ja|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "50267": {
86
- "content": "<|pt|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "50268": {
94
- "content": "<|tr|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "50269": {
102
- "content": "<|pl|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "50270": {
110
- "content": "<|ca|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "50271": {
118
- "content": "<|nl|>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "50272": {
126
- "content": "<|ar|>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "50273": {
134
- "content": "<|sv|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "50274": {
142
- "content": "<|it|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "50275": {
150
- "content": "<|id|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "50276": {
158
- "content": "<|hi|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "50277": {
166
- "content": "<|fi|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "50278": {
174
- "content": "<|vi|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "50279": {
182
- "content": "<|he|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "50280": {
190
- "content": "<|uk|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "50281": {
198
- "content": "<|el|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "50282": {
206
- "content": "<|ms|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "50283": {
214
- "content": "<|cs|>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": false,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "50284": {
222
- "content": "<|ro|>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": false,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "50285": {
230
- "content": "<|da|>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": false,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "50286": {
238
- "content": "<|hu|>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": false,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "50287": {
246
- "content": "<|ta|>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": false,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "50288": {
254
- "content": "<|no|>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": false,
258
- "single_word": false,
259
- "special": true
260
- },
261
- "50289": {
262
- "content": "<|th|>",
263
- "lstrip": false,
264
- "normalized": false,
265
- "rstrip": false,
266
- "single_word": false,
267
- "special": true
268
- },
269
- "50290": {
270
- "content": "<|ur|>",
271
- "lstrip": false,
272
- "normalized": false,
273
- "rstrip": false,
274
- "single_word": false,
275
- "special": true
276
- },
277
- "50291": {
278
- "content": "<|hr|>",
279
- "lstrip": false,
280
- "normalized": false,
281
- "rstrip": false,
282
- "single_word": false,
283
- "special": true
284
- },
285
- "50292": {
286
- "content": "<|bg|>",
287
- "lstrip": false,
288
- "normalized": false,
289
- "rstrip": false,
290
- "single_word": false,
291
- "special": true
292
- },
293
- "50293": {
294
- "content": "<|lt|>",
295
- "lstrip": false,
296
- "normalized": false,
297
- "rstrip": false,
298
- "single_word": false,
299
- "special": true
300
- },
301
- "50294": {
302
- "content": "<|la|>",
303
- "lstrip": false,
304
- "normalized": false,
305
- "rstrip": false,
306
- "single_word": false,
307
- "special": true
308
- },
309
- "50295": {
310
- "content": "<|mi|>",
311
- "lstrip": false,
312
- "normalized": false,
313
- "rstrip": false,
314
- "single_word": false,
315
- "special": true
316
- },
317
- "50296": {
318
- "content": "<|ml|>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": false,
322
- "single_word": false,
323
- "special": true
324
- },
325
- "50297": {
326
- "content": "<|cy|>",
327
- "lstrip": false,
328
- "normalized": false,
329
- "rstrip": false,
330
- "single_word": false,
331
- "special": true
332
- },
333
- "50298": {
334
- "content": "<|sk|>",
335
- "lstrip": false,
336
- "normalized": false,
337
- "rstrip": false,
338
- "single_word": false,
339
- "special": true
340
- },
341
- "50299": {
342
- "content": "<|te|>",
343
- "lstrip": false,
344
- "normalized": false,
345
- "rstrip": false,
346
- "single_word": false,
347
- "special": true
348
- },
349
- "50300": {
350
- "content": "<|fa|>",
351
- "lstrip": false,
352
- "normalized": false,
353
- "rstrip": false,
354
- "single_word": false,
355
- "special": true
356
- },
357
- "50301": {
358
- "content": "<|lv|>",
359
- "lstrip": false,
360
- "normalized": false,
361
- "rstrip": false,
362
- "single_word": false,
363
- "special": true
364
- },
365
- "50302": {
366
- "content": "<|bn|>",
367
- "lstrip": false,
368
- "normalized": false,
369
- "rstrip": false,
370
- "single_word": false,
371
- "special": true
372
- },
373
- "50303": {
374
- "content": "<|sr|>",
375
- "lstrip": false,
376
- "normalized": false,
377
- "rstrip": false,
378
- "single_word": false,
379
- "special": true
380
- },
381
- "50304": {
382
- "content": "<|az|>",
383
- "lstrip": false,
384
- "normalized": false,
385
- "rstrip": false,
386
- "single_word": false,
387
- "special": true
388
- },
389
- "50305": {
390
- "content": "<|sl|>",
391
- "lstrip": false,
392
- "normalized": false,
393
- "rstrip": false,
394
- "single_word": false,
395
- "special": true
396
- },
397
- "50306": {
398
- "content": "<|kn|>",
399
- "lstrip": false,
400
- "normalized": false,
401
- "rstrip": false,
402
- "single_word": false,
403
- "special": true
404
- },
405
- "50307": {
406
- "content": "<|et|>",
407
- "lstrip": false,
408
- "normalized": false,
409
- "rstrip": false,
410
- "single_word": false,
411
- "special": true
412
- },
413
- "50308": {
414
- "content": "<|mk|>",
415
- "lstrip": false,
416
- "normalized": false,
417
- "rstrip": false,
418
- "single_word": false,
419
- "special": true
420
- },
421
- "50309": {
422
- "content": "<|br|>",
423
- "lstrip": false,
424
- "normalized": false,
425
- "rstrip": false,
426
- "single_word": false,
427
- "special": true
428
- },
429
- "50310": {
430
- "content": "<|eu|>",
431
- "lstrip": false,
432
- "normalized": false,
433
- "rstrip": false,
434
- "single_word": false,
435
- "special": true
436
- },
437
- "50311": {
438
- "content": "<|is|>",
439
- "lstrip": false,
440
- "normalized": false,
441
- "rstrip": false,
442
- "single_word": false,
443
- "special": true
444
- },
445
- "50312": {
446
- "content": "<|hy|>",
447
- "lstrip": false,
448
- "normalized": false,
449
- "rstrip": false,
450
- "single_word": false,
451
- "special": true
452
- },
453
- "50313": {
454
- "content": "<|ne|>",
455
- "lstrip": false,
456
- "normalized": false,
457
- "rstrip": false,
458
- "single_word": false,
459
- "special": true
460
- },
461
- "50314": {
462
- "content": "<|mn|>",
463
- "lstrip": false,
464
- "normalized": false,
465
- "rstrip": false,
466
- "single_word": false,
467
- "special": true
468
- },
469
- "50315": {
470
- "content": "<|bs|>",
471
- "lstrip": false,
472
- "normalized": false,
473
- "rstrip": false,
474
- "single_word": false,
475
- "special": true
476
- },
477
- "50316": {
478
- "content": "<|kk|>",
479
- "lstrip": false,
480
- "normalized": false,
481
- "rstrip": false,
482
- "single_word": false,
483
- "special": true
484
- },
485
- "50317": {
486
- "content": "<|sq|>",
487
- "lstrip": false,
488
- "normalized": false,
489
- "rstrip": false,
490
- "single_word": false,
491
- "special": true
492
- },
493
- "50318": {
494
- "content": "<|sw|>",
495
- "lstrip": false,
496
- "normalized": false,
497
- "rstrip": false,
498
- "single_word": false,
499
- "special": true
500
- },
501
- "50319": {
502
- "content": "<|gl|>",
503
- "lstrip": false,
504
- "normalized": false,
505
- "rstrip": false,
506
- "single_word": false,
507
- "special": true
508
- },
509
- "50320": {
510
- "content": "<|mr|>",
511
- "lstrip": false,
512
- "normalized": false,
513
- "rstrip": false,
514
- "single_word": false,
515
- "special": true
516
- },
517
- "50321": {
518
- "content": "<|pa|>",
519
- "lstrip": false,
520
- "normalized": false,
521
- "rstrip": false,
522
- "single_word": false,
523
- "special": true
524
- },
525
- "50322": {
526
- "content": "<|si|>",
527
- "lstrip": false,
528
- "normalized": false,
529
- "rstrip": false,
530
- "single_word": false,
531
- "special": true
532
- },
533
- "50323": {
534
- "content": "<|km|>",
535
- "lstrip": false,
536
- "normalized": false,
537
- "rstrip": false,
538
- "single_word": false,
539
- "special": true
540
- },
541
- "50324": {
542
- "content": "<|sn|>",
543
- "lstrip": false,
544
- "normalized": false,
545
- "rstrip": false,
546
- "single_word": false,
547
- "special": true
548
- },
549
- "50325": {
550
- "content": "<|yo|>",
551
- "lstrip": false,
552
- "normalized": false,
553
- "rstrip": false,
554
- "single_word": false,
555
- "special": true
556
- },
557
- "50326": {
558
- "content": "<|so|>",
559
- "lstrip": false,
560
- "normalized": false,
561
- "rstrip": false,
562
- "single_word": false,
563
- "special": true
564
- },
565
- "50327": {
566
- "content": "<|af|>",
567
- "lstrip": false,
568
- "normalized": false,
569
- "rstrip": false,
570
- "single_word": false,
571
- "special": true
572
- },
573
- "50328": {
574
- "content": "<|oc|>",
575
- "lstrip": false,
576
- "normalized": false,
577
- "rstrip": false,
578
- "single_word": false,
579
- "special": true
580
- },
581
- "50329": {
582
- "content": "<|ka|>",
583
- "lstrip": false,
584
- "normalized": false,
585
- "rstrip": false,
586
- "single_word": false,
587
- "special": true
588
- },
589
- "50330": {
590
- "content": "<|be|>",
591
- "lstrip": false,
592
- "normalized": false,
593
- "rstrip": false,
594
- "single_word": false,
595
- "special": true
596
- },
597
- "50331": {
598
- "content": "<|tg|>",
599
- "lstrip": false,
600
- "normalized": false,
601
- "rstrip": false,
602
- "single_word": false,
603
- "special": true
604
- },
605
- "50332": {
606
- "content": "<|sd|>",
607
- "lstrip": false,
608
- "normalized": false,
609
- "rstrip": false,
610
- "single_word": false,
611
- "special": true
612
- },
613
- "50333": {
614
- "content": "<|gu|>",
615
- "lstrip": false,
616
- "normalized": false,
617
- "rstrip": false,
618
- "single_word": false,
619
- "special": true
620
- },
621
- "50334": {
622
- "content": "<|am|>",
623
- "lstrip": false,
624
- "normalized": false,
625
- "rstrip": false,
626
- "single_word": false,
627
- "special": true
628
- },
629
- "50335": {
630
- "content": "<|yi|>",
631
- "lstrip": false,
632
- "normalized": false,
633
- "rstrip": false,
634
- "single_word": false,
635
- "special": true
636
- },
637
- "50336": {
638
- "content": "<|lo|>",
639
- "lstrip": false,
640
- "normalized": false,
641
- "rstrip": false,
642
- "single_word": false,
643
- "special": true
644
- },
645
- "50337": {
646
- "content": "<|uz|>",
647
- "lstrip": false,
648
- "normalized": false,
649
- "rstrip": false,
650
- "single_word": false,
651
- "special": true
652
- },
653
- "50338": {
654
- "content": "<|fo|>",
655
- "lstrip": false,
656
- "normalized": false,
657
- "rstrip": false,
658
- "single_word": false,
659
- "special": true
660
- },
661
- "50339": {
662
- "content": "<|ht|>",
663
- "lstrip": false,
664
- "normalized": false,
665
- "rstrip": false,
666
- "single_word": false,
667
- "special": true
668
- },
669
- "50340": {
670
- "content": "<|ps|>",
671
- "lstrip": false,
672
- "normalized": false,
673
- "rstrip": false,
674
- "single_word": false,
675
- "special": true
676
- },
677
- "50341": {
678
- "content": "<|tk|>",
679
- "lstrip": false,
680
- "normalized": false,
681
- "rstrip": false,
682
- "single_word": false,
683
- "special": true
684
- },
685
- "50342": {
686
- "content": "<|nn|>",
687
- "lstrip": false,
688
- "normalized": false,
689
- "rstrip": false,
690
- "single_word": false,
691
- "special": true
692
- },
693
- "50343": {
694
- "content": "<|mt|>",
695
- "lstrip": false,
696
- "normalized": false,
697
- "rstrip": false,
698
- "single_word": false,
699
- "special": true
700
- },
701
- "50344": {
702
- "content": "<|sa|>",
703
- "lstrip": false,
704
- "normalized": false,
705
- "rstrip": false,
706
- "single_word": false,
707
- "special": true
708
- },
709
- "50345": {
710
- "content": "<|lb|>",
711
- "lstrip": false,
712
- "normalized": false,
713
- "rstrip": false,
714
- "single_word": false,
715
- "special": true
716
- },
717
- "50346": {
718
- "content": "<|my|>",
719
- "lstrip": false,
720
- "normalized": false,
721
- "rstrip": false,
722
- "single_word": false,
723
- "special": true
724
- },
725
- "50347": {
726
- "content": "<|bo|>",
727
- "lstrip": false,
728
- "normalized": false,
729
- "rstrip": false,
730
- "single_word": false,
731
- "special": true
732
- },
733
- "50348": {
734
- "content": "<|tl|>",
735
- "lstrip": false,
736
- "normalized": false,
737
- "rstrip": false,
738
- "single_word": false,
739
- "special": true
740
- },
741
- "50349": {
742
- "content": "<|mg|>",
743
- "lstrip": false,
744
- "normalized": false,
745
- "rstrip": false,
746
- "single_word": false,
747
- "special": true
748
- },
749
- "50350": {
750
- "content": "<|as|>",
751
- "lstrip": false,
752
- "normalized": false,
753
- "rstrip": false,
754
- "single_word": false,
755
- "special": true
756
- },
757
- "50351": {
758
- "content": "<|tt|>",
759
- "lstrip": false,
760
- "normalized": false,
761
- "rstrip": false,
762
- "single_word": false,
763
- "special": true
764
- },
765
- "50352": {
766
- "content": "<|haw|>",
767
- "lstrip": false,
768
- "normalized": false,
769
- "rstrip": false,
770
- "single_word": false,
771
- "special": true
772
- },
773
- "50353": {
774
- "content": "<|ln|>",
775
- "lstrip": false,
776
- "normalized": false,
777
- "rstrip": false,
778
- "single_word": false,
779
- "special": true
780
- },
781
- "50354": {
782
- "content": "<|ha|>",
783
- "lstrip": false,
784
- "normalized": false,
785
- "rstrip": false,
786
- "single_word": false,
787
- "special": true
788
- },
789
- "50355": {
790
- "content": "<|ba|>",
791
- "lstrip": false,
792
- "normalized": false,
793
- "rstrip": false,
794
- "single_word": false,
795
- "special": true
796
- },
797
- "50356": {
798
- "content": "<|jw|>",
799
- "lstrip": false,
800
- "normalized": false,
801
- "rstrip": false,
802
- "single_word": false,
803
- "special": true
804
- },
805
- "50357": {
806
- "content": "<|su|>",
807
- "lstrip": false,
808
- "normalized": false,
809
- "rstrip": false,
810
- "single_word": false,
811
- "special": true
812
- },
813
- "50358": {
814
- "content": "<|translate|>",
815
- "lstrip": false,
816
- "normalized": false,
817
- "rstrip": false,
818
- "single_word": false,
819
- "special": true
820
- },
821
- "50359": {
822
- "content": "<|transcribe|>",
823
- "lstrip": false,
824
- "normalized": false,
825
- "rstrip": false,
826
- "single_word": false,
827
- "special": true
828
- },
829
- "50360": {
830
- "content": "<|startoflm|>",
831
- "lstrip": false,
832
- "normalized": false,
833
- "rstrip": false,
834
- "single_word": false,
835
- "special": true
836
- },
837
- "50361": {
838
- "content": "<|startofprev|>",
839
- "lstrip": false,
840
- "normalized": false,
841
- "rstrip": false,
842
- "single_word": false,
843
- "special": true
844
- },
845
- "50362": {
846
- "content": "<|nocaptions|>",
847
- "lstrip": false,
848
- "normalized": false,
849
- "rstrip": false,
850
- "single_word": false,
851
- "special": true
852
- },
853
- "50363": {
854
- "content": "<|notimestamps|>",
855
- "lstrip": false,
856
- "normalized": false,
857
- "rstrip": false,
858
- "single_word": false,
859
- "special": true
860
- }
861
- },
862
- "additional_special_tokens": [
863
- "<|endoftext|>",
864
- "<|startoftranscript|>",
865
- "<|en|>",
866
- "<|zh|>",
867
- "<|de|>",
868
- "<|es|>",
869
- "<|ru|>",
870
- "<|ko|>",
871
- "<|fr|>",
872
- "<|ja|>",
873
- "<|pt|>",
874
- "<|tr|>",
875
- "<|pl|>",
876
- "<|ca|>",
877
- "<|nl|>",
878
- "<|ar|>",
879
- "<|sv|>",
880
- "<|it|>",
881
- "<|id|>",
882
- "<|hi|>",
883
- "<|fi|>",
884
- "<|vi|>",
885
- "<|he|>",
886
- "<|uk|>",
887
- "<|el|>",
888
- "<|ms|>",
889
- "<|cs|>",
890
- "<|ro|>",
891
- "<|da|>",
892
- "<|hu|>",
893
- "<|ta|>",
894
- "<|no|>",
895
- "<|th|>",
896
- "<|ur|>",
897
- "<|hr|>",
898
- "<|bg|>",
899
- "<|lt|>",
900
- "<|la|>",
901
- "<|mi|>",
902
- "<|ml|>",
903
- "<|cy|>",
904
- "<|sk|>",
905
- "<|te|>",
906
- "<|fa|>",
907
- "<|lv|>",
908
- "<|bn|>",
909
- "<|sr|>",
910
- "<|az|>",
911
- "<|sl|>",
912
- "<|kn|>",
913
- "<|et|>",
914
- "<|mk|>",
915
- "<|br|>",
916
- "<|eu|>",
917
- "<|is|>",
918
- "<|hy|>",
919
- "<|ne|>",
920
- "<|mn|>",
921
- "<|bs|>",
922
- "<|kk|>",
923
- "<|sq|>",
924
- "<|sw|>",
925
- "<|gl|>",
926
- "<|mr|>",
927
- "<|pa|>",
928
- "<|si|>",
929
- "<|km|>",
930
- "<|sn|>",
931
- "<|yo|>",
932
- "<|so|>",
933
- "<|af|>",
934
- "<|oc|>",
935
- "<|ka|>",
936
- "<|be|>",
937
- "<|tg|>",
938
- "<|sd|>",
939
- "<|gu|>",
940
- "<|am|>",
941
- "<|yi|>",
942
- "<|lo|>",
943
- "<|uz|>",
944
- "<|fo|>",
945
- "<|ht|>",
946
- "<|ps|>",
947
- "<|tk|>",
948
- "<|nn|>",
949
- "<|mt|>",
950
- "<|sa|>",
951
- "<|lb|>",
952
- "<|my|>",
953
- "<|bo|>",
954
- "<|tl|>",
955
- "<|mg|>",
956
- "<|as|>",
957
- "<|tt|>",
958
- "<|haw|>",
959
- "<|ln|>",
960
- "<|ha|>",
961
- "<|ba|>",
962
- "<|jw|>",
963
- "<|su|>",
964
- "<|translate|>",
965
- "<|transcribe|>",
966
- "<|startoflm|>",
967
- "<|startofprev|>",
968
- "<|nocaptions|>",
969
- "<|notimestamps|>"
970
- ],
971
- "bos_token": "<|endoftext|>",
972
- "clean_up_tokenization_spaces": true,
973
- "eos_token": "<|endoftext|>",
974
- "errors": "replace",
975
- "model_max_length": 1024,
976
- "pad_token": "<|endoftext|>",
977
- "processor_class": "WhisperProcessor",
978
- "return_attention_mask": false,
979
- "tokenizer_class": "WhisperTokenizer",
980
- "unk_token": "<|endoftext|>"
981
- }
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50257": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50258": {
14
+ "content": "<|startoftranscript|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "50259": {
22
+ "content": "<|en|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "50260": {
30
+ "content": "<|zh|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50261": {
38
+ "content": "<|de|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "50262": {
46
+ "content": "<|es|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "50263": {
54
+ "content": "<|ru|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "50264": {
62
+ "content": "<|ko|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "50265": {
70
+ "content": "<|fr|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "50266": {
78
+ "content": "<|ja|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "50267": {
86
+ "content": "<|pt|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "50268": {
94
+ "content": "<|tr|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "50269": {
102
+ "content": "<|pl|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "50270": {
110
+ "content": "<|ca|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "50271": {
118
+ "content": "<|nl|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "50272": {
126
+ "content": "<|ar|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "50273": {
134
+ "content": "<|sv|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "50274": {
142
+ "content": "<|it|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "50275": {
150
+ "content": "<|id|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "50276": {
158
+ "content": "<|hi|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "50277": {
166
+ "content": "<|fi|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "50278": {
174
+ "content": "<|vi|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "50279": {
182
+ "content": "<|iw|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "50280": {
190
+ "content": "<|uk|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "50281": {
198
+ "content": "<|el|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "50282": {
206
+ "content": "<|ms|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "50283": {
214
+ "content": "<|cs|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "50284": {
222
+ "content": "<|ro|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "50285": {
230
+ "content": "<|da|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "50286": {
238
+ "content": "<|hu|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "50287": {
246
+ "content": "<|ta|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "50288": {
254
+ "content": "<|no|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "50289": {
262
+ "content": "<|th|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "50290": {
270
+ "content": "<|ur|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "50291": {
278
+ "content": "<|hr|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "50292": {
286
+ "content": "<|bg|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "50293": {
294
+ "content": "<|lt|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "50294": {
302
+ "content": "<|la|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "50295": {
310
+ "content": "<|mi|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "50296": {
318
+ "content": "<|ml|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "50297": {
326
+ "content": "<|cy|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "50298": {
334
+ "content": "<|sk|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "50299": {
342
+ "content": "<|te|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "50300": {
350
+ "content": "<|fa|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "50301": {
358
+ "content": "<|lv|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "50302": {
366
+ "content": "<|bn|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "50303": {
374
+ "content": "<|sr|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "50304": {
382
+ "content": "<|az|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "50305": {
390
+ "content": "<|sl|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "50306": {
398
+ "content": "<|kn|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "50307": {
406
+ "content": "<|et|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "50308": {
414
+ "content": "<|mk|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "50309": {
422
+ "content": "<|br|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "50310": {
430
+ "content": "<|eu|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "50311": {
438
+ "content": "<|is|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "50312": {
446
+ "content": "<|hy|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "50313": {
454
+ "content": "<|ne|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "50314": {
462
+ "content": "<|mn|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "50315": {
470
+ "content": "<|bs|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "50316": {
478
+ "content": "<|kk|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "50317": {
486
+ "content": "<|sq|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "50318": {
494
+ "content": "<|sw|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "50319": {
502
+ "content": "<|gl|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "50320": {
510
+ "content": "<|mr|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "50321": {
518
+ "content": "<|pa|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "50322": {
526
+ "content": "<|si|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "50323": {
534
+ "content": "<|km|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "50324": {
542
+ "content": "<|sn|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "50325": {
550
+ "content": "<|yo|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "50326": {
558
+ "content": "<|so|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "50327": {
566
+ "content": "<|af|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "50328": {
574
+ "content": "<|oc|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "50329": {
582
+ "content": "<|ka|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "50330": {
590
+ "content": "<|be|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "50331": {
598
+ "content": "<|tg|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "50332": {
606
+ "content": "<|sd|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "50333": {
614
+ "content": "<|gu|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "50334": {
622
+ "content": "<|am|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "50335": {
630
+ "content": "<|yi|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "50336": {
638
+ "content": "<|lo|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "50337": {
646
+ "content": "<|uz|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "50338": {
654
+ "content": "<|fo|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "50339": {
662
+ "content": "<|ht|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "50340": {
670
+ "content": "<|ps|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "50341": {
678
+ "content": "<|tk|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "50342": {
686
+ "content": "<|nn|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "50343": {
694
+ "content": "<|mt|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "50344": {
702
+ "content": "<|sa|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "50345": {
710
+ "content": "<|lb|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "50346": {
718
+ "content": "<|my|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "50347": {
726
+ "content": "<|bo|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "50348": {
734
+ "content": "<|tl|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "50349": {
742
+ "content": "<|mg|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "50350": {
750
+ "content": "<|as|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "50351": {
758
+ "content": "<|tt|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "50352": {
766
+ "content": "<|haw|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "50353": {
774
+ "content": "<|ln|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "50354": {
782
+ "content": "<|ha|>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "50355": {
790
+ "content": "<|ba|>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "50356": {
798
+ "content": "<|jw|>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "50357": {
806
+ "content": "<|su|>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "50358": {
814
+ "content": "<|translate|>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "50359": {
822
+ "content": "<|transcribe|>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "50360": {
830
+ "content": "<|startoflm|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "50361": {
838
+ "content": "<|startofprev|>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "50362": {
846
+ "content": "<|nocaptions|>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "50363": {
854
+ "content": "<|notimestamps|>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ }
861
+ },
862
+ "additional_special_tokens": [
863
+ "<|endoftext|>",
864
+ "<|startoftranscript|>",
865
+ "<|en|>",
866
+ "<|zh|>",
867
+ "<|de|>",
868
+ "<|es|>",
869
+ "<|ru|>",
870
+ "<|ko|>",
871
+ "<|fr|>",
872
+ "<|ja|>",
873
+ "<|pt|>",
874
+ "<|tr|>",
875
+ "<|pl|>",
876
+ "<|ca|>",
877
+ "<|nl|>",
878
+ "<|ar|>",
879
+ "<|sv|>",
880
+ "<|it|>",
881
+ "<|id|>",
882
+ "<|hi|>",
883
+ "<|fi|>",
884
+ "<|vi|>",
885
+ "<|iw|>",
886
+ "<|uk|>",
887
+ "<|el|>",
888
+ "<|ms|>",
889
+ "<|cs|>",
890
+ "<|ro|>",
891
+ "<|da|>",
892
+ "<|hu|>",
893
+ "<|ta|>",
894
+ "<|no|>",
895
+ "<|th|>",
896
+ "<|ur|>",
897
+ "<|hr|>",
898
+ "<|bg|>",
899
+ "<|lt|>",
900
+ "<|la|>",
901
+ "<|mi|>",
902
+ "<|ml|>",
903
+ "<|cy|>",
904
+ "<|sk|>",
905
+ "<|te|>",
906
+ "<|fa|>",
907
+ "<|lv|>",
908
+ "<|bn|>",
909
+ "<|sr|>",
910
+ "<|az|>",
911
+ "<|sl|>",
912
+ "<|kn|>",
913
+ "<|et|>",
914
+ "<|mk|>",
915
+ "<|br|>",
916
+ "<|eu|>",
917
+ "<|is|>",
918
+ "<|hy|>",
919
+ "<|ne|>",
920
+ "<|mn|>",
921
+ "<|bs|>",
922
+ "<|kk|>",
923
+ "<|sq|>",
924
+ "<|sw|>",
925
+ "<|gl|>",
926
+ "<|mr|>",
927
+ "<|pa|>",
928
+ "<|si|>",
929
+ "<|km|>",
930
+ "<|sn|>",
931
+ "<|yo|>",
932
+ "<|so|>",
933
+ "<|af|>",
934
+ "<|oc|>",
935
+ "<|ka|>",
936
+ "<|be|>",
937
+ "<|tg|>",
938
+ "<|sd|>",
939
+ "<|gu|>",
940
+ "<|am|>",
941
+ "<|yi|>",
942
+ "<|lo|>",
943
+ "<|uz|>",
944
+ "<|fo|>",
945
+ "<|ht|>",
946
+ "<|ps|>",
947
+ "<|tk|>",
948
+ "<|nn|>",
949
+ "<|mt|>",
950
+ "<|sa|>",
951
+ "<|lb|>",
952
+ "<|my|>",
953
+ "<|bo|>",
954
+ "<|tl|>",
955
+ "<|mg|>",
956
+ "<|as|>",
957
+ "<|tt|>",
958
+ "<|haw|>",
959
+ "<|ln|>",
960
+ "<|ha|>",
961
+ "<|ba|>",
962
+ "<|jw|>",
963
+ "<|su|>",
964
+ "<|translate|>",
965
+ "<|transcribe|>",
966
+ "<|startoflm|>",
967
+ "<|startofprev|>",
968
+ "<|nocaptions|>",
969
+ "<|notimestamps|>"
970
+ ],
971
+ "bos_token": "<|endoftext|>",
972
+ "clean_up_tokenization_spaces": true,
973
+ "eos_token": "<|endoftext|>",
974
+ "errors": "replace",
975
+ "model_max_length": 448,
976
+ "pad_token": "<|endoftext|>",
977
+ "processor_class": "WhisperProcessor",
978
+ "return_attention_mask": false,
979
+ "tokenizer_class": "WhisperTokenizer",
980
+ "unk_token": ""
981
+ }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff