BauyrjanQ commited on
Commit
e4f298e
1 Parent(s): 1074f88

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +22 -0
  3. tokenizer_config.json +13 -0
  4. vocab.json +145 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 142,
3
+ "<s>": 141
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "[PAD]",
21
+ "unk_token": "[UNK]"
22
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "target_lang": "kaz",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kaz": {
3
+ "\t": 0,
4
+ "\n": 1,
5
+ "\r": 2,
6
+ "#": 4,
7
+ "&": 5,
8
+ "(": 6,
9
+ ")": 7,
10
+ "+": 8,
11
+ "/": 9,
12
+ "0": 10,
13
+ "1": 11,
14
+ "2": 12,
15
+ "3": 13,
16
+ "4": 14,
17
+ "5": 15,
18
+ "6": 16,
19
+ "7": 17,
20
+ "8": 18,
21
+ "9": 19,
22
+ "[": 20,
23
+ "[PAD]": 140,
24
+ "[UNK]": 139,
25
+ "\\": 21,
26
+ "]": 22,
27
+ "_": 23,
28
+ "a": 24,
29
+ "b": 25,
30
+ "c": 26,
31
+ "e": 27,
32
+ "f": 28,
33
+ "i": 29,
34
+ "k": 30,
35
+ "m": 31,
36
+ "n": 32,
37
+ "o": 33,
38
+ "p": 34,
39
+ "r": 35,
40
+ "s": 36,
41
+ "t": 37,
42
+ "y": 38,
43
+ "z": 39,
44
+ "{": 40,
45
+ "|": 3,
46
+ "}": 41,
47
+ "~": 42,
48
+ " ": 43,
49
+ "¥": 44,
50
+ "©": 45,
51
+ "«": 46,
52
+ "¬": 47,
53
+ "­": 48,
54
+ "·": 49,
55
+ "»": 50,
56
+ "ë": 51,
57
+ "ŋ": 52,
58
+ "ɕ": 53,
59
+ "ə": 54,
60
+ "ɵ": 55,
61
+ "ʨ": 56,
62
+ "̀": 57,
63
+ "́": 58,
64
+ "̃": 59,
65
+ "̆": 60,
66
+ "̇": 61,
67
+ "̈": 62,
68
+ "̜": 63,
69
+ "̟": 64,
70
+ "̥": 65,
71
+ "̩": 66,
72
+ "̰": 67,
73
+ "̶": 68,
74
+ "̹": 69,
75
+ "υ": 70,
76
+ "а": 71,
77
+ "б": 72,
78
+ "в": 73,
79
+ "г": 74,
80
+ "д": 75,
81
+ "е": 76,
82
+ "ж": 77,
83
+ "з": 78,
84
+ "и": 79,
85
+ "й": 80,
86
+ "к": 81,
87
+ "л": 82,
88
+ "м": 83,
89
+ "н": 84,
90
+ "о": 85,
91
+ "п": 86,
92
+ "р": 87,
93
+ "с": 88,
94
+ "т": 89,
95
+ "у": 90,
96
+ "ф": 91,
97
+ "х": 92,
98
+ "ц": 93,
99
+ "ч": 94,
100
+ "ш": 95,
101
+ "щ": 96,
102
+ "ъ": 97,
103
+ "ы": 98,
104
+ "ь": 99,
105
+ "э": 100,
106
+ "ю": 101,
107
+ "я": 102,
108
+ "ё": 103,
109
+ "і": 104,
110
+ "ї": 105,
111
+ "ў": 106,
112
+ "ѳ": 107,
113
+ "ғ": 108,
114
+ "қ": 109,
115
+ "ң": 110,
116
+ "ү": 111,
117
+ "ұ": 112,
118
+ "һ": 113,
119
+ "ӊ": 114,
120
+ "ӏ": 115,
121
+ "ә": 116,
122
+ "ө": 117,
123
+ "​": 118,
124
+ "‎": 119,
125
+ "‐": 120,
126
+ "‒": 121,
127
+ "–": 122,
128
+ "—": 123,
129
+ "―": 124,
130
+ "’": 125,
131
+ "‚": 126,
132
+ "„": 127,
133
+ "…": 128,
134
+ "№": 129,
135
+ "−": 130,
136
+ "─": 131,
137
+ "●": 132,
138
+ "☺": 133,
139
+ "♥": 134,
140
+ "⠀": 135,
141
+ "": 136,
142
+ "": 137,
143
+ "-": 138
144
+ }
145
+ }