Hugging Face's logo

sepid72
/
wav2vec2-large-mms-1b-persian-colab

Model card Files Community
sepid72 commited on
Commit
4fbbea3
·
verified ·
1 Parent(s): e5df273

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +47 -0
  4. vocab.json +134 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 131,
3
+ "<s>": 130
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "129": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "130": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "131": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": "fa",
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "fa": {
3
+ "#": 1,
4
+ "&": 2,
5
+ "(": 3,
6
+ ")": 4,
7
+ "=": 5,
8
+ "[PAD]": 129,
9
+ "[UNK]": 128,
10
+ "_": 6,
11
+ "a": 7,
12
+ "b": 8,
13
+ "c": 9,
14
+ "d": 10,
15
+ "e": 11,
16
+ "f": 12,
17
+ "g": 13,
18
+ "h": 14,
19
+ "i": 15,
20
+ "k": 16,
21
+ "l": 17,
22
+ "m": 18,
23
+ "n": 19,
24
+ "o": 20,
25
+ "p": 21,
26
+ "q": 22,
27
+ "r": 23,
28
+ "s": 24,
29
+ "t": 25,
30
+ "u": 26,
31
+ "v": 27,
32
+ "w": 28,
33
+ "x": 29,
34
+ "y": 30,
35
+ "z": 31,
36
+ "|": 0,
37
+ "«": 32,
38
+ "»": 33,
39
+ "ā": 34,
40
+ "š": 35,
41
+ "،": 36,
42
+ "؛": 37,
43
+ "؟": 38,
44
+ "ء": 39,
45
+ "آ": 40,
46
+ "أ": 41,
47
+ "ؤ": 42,
48
+ "ئ": 43,
49
+ "ا": 44,
50
+ "ب": 45,
51
+ "ة": 46,
52
+ "ت": 47,
53
+ "ث": 48,
54
+ "ج": 49,
55
+ "ح": 50,
56
+ "خ": 51,
57
+ "د": 52,
58
+ "ذ": 53,
59
+ "ر": 54,
60
+ "ز": 55,
61
+ "س": 56,
62
+ "ش": 57,
63
+ "ص": 58,
64
+ "ض": 59,
65
+ "ط": 60,
66
+ "ظ": 61,
67
+ "ع": 62,
68
+ "غ": 63,
69
+ "ـ": 64,
70
+ "ف": 65,
71
+ "ق": 66,
72
+ "ك": 67,
73
+ "ل": 68,
74
+ "م": 69,
75
+ "ن": 70,
76
+ "ه": 71,
77
+ "و": 72,
78
+ "ى": 73,
79
+ "ي": 74,
80
+ "ً": 75,
81
+ "ٌ": 76,
82
+ "َ": 77,
83
+ "ُ": 78,
84
+ "ِ": 79,
85
+ "ّ": 80,
86
+ "ْ": 81,
87
+ "ٔ": 82,
88
+ "٬": 83,
89
+ "پ": 84,
90
+ "چ": 85,
91
+ "ژ": 86,
92
+ "ک": 87,
93
+ "گ": 88,
94
+ "ۀ": 89,
95
+ "ی": 90,
96
+ "ے": 91,
97
+ "ە": 92,
98
+ "–": 93,
99
+ "…": 94,
100
+ "ﭘ": 95,
101
+ "ﮐ": 96,
102
+ "ﮔ": 97,
103
+ "ﯽ": 98,
104
+ "ﯾ": 99,
105
+ "ﯿ": 100,
106
+ "ﺍ": 101,
107
+ "ﺎ": 102,
108
+ "ﺑ": 103,
109
+ "ﺒ": 104,
110
+ "ﺖ": 105,
111
+ "ﺘ": 106,
112
+ "ﺧ": 107,
113
+ "ﺩ": 108,
114
+ "ﺪ": 109,
115
+ "ﺭ": 110,
116
+ "ﺮ": 111,
117
+ "ﺱ": 112,
118
+ "ﺴ": 113,
119
+ "ﺷ": 114,
120
+ "ﺸ": 115,
121
+ "ﻀ": 116,
122
+ "ﻋ": 117,
123
+ "ﻌ": 118,
124
+ "ﻟ": 119,
125
+ "ﻡ": 120,
126
+ "ﻢ": 121,
127
+ "ﻤ": 122,
128
+ "ﻥ": 123,
129
+ "ﻧ": 124,
130
+ "ﻪ": 125,
131
+ "ﻭ": 126,
132
+ "ﻮ": 127
133
+ }
134
+ }