BauyrjanQ commited on
Commit
72733ec
1 Parent(s): 7081110

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 +130 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 127,
3
+ "<s>": 126
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 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "kaz": {
3
+ "\n": 0,
4
+ "/": 2,
5
+ "[": 3,
6
+ "[PAD]": 125,
7
+ "[UNK]": 124,
8
+ "]": 4,
9
+ "a": 5,
10
+ "b": 6,
11
+ "c": 7,
12
+ "d": 8,
13
+ "e": 9,
14
+ "f": 10,
15
+ "g": 11,
16
+ "h": 12,
17
+ "i": 13,
18
+ "j": 14,
19
+ "k": 15,
20
+ "l": 16,
21
+ "m": 17,
22
+ "n": 18,
23
+ "o": 19,
24
+ "p": 20,
25
+ "q": 21,
26
+ "r": 22,
27
+ "s": 23,
28
+ "t": 24,
29
+ "u": 25,
30
+ "v": 26,
31
+ "w": 27,
32
+ "x": 28,
33
+ "y": 29,
34
+ "z": 30,
35
+ "{": 31,
36
+ "|": 1,
37
+ "}": 32,
38
+ "®": 33,
39
+ "»": 34,
40
+ "ã": 35,
41
+ "ä": 36,
42
+ "ó": 37,
43
+ "ö": 38,
44
+ "ü": 39,
45
+ "ğ": 40,
46
+ "ū": 41,
47
+ "ə": 42,
48
+ "ɵ": 43,
49
+ "ϵ": 44,
50
+ "а": 45,
51
+ "б": 46,
52
+ "в": 47,
53
+ "г": 48,
54
+ "д": 49,
55
+ "е": 50,
56
+ "ж": 51,
57
+ "з": 52,
58
+ "и": 53,
59
+ "й": 54,
60
+ "к": 55,
61
+ "л": 56,
62
+ "м": 57,
63
+ "н": 58,
64
+ "о": 59,
65
+ "п": 60,
66
+ "р": 61,
67
+ "с": 62,
68
+ "т": 63,
69
+ "у": 64,
70
+ "ф": 65,
71
+ "х": 66,
72
+ "ц": 67,
73
+ "ч": 68,
74
+ "ш": 69,
75
+ "щ": 70,
76
+ "ъ": 71,
77
+ "ы": 72,
78
+ "ь": 73,
79
+ "э": 74,
80
+ "ю": 75,
81
+ "я": 76,
82
+ "ё": 77,
83
+ "і": 78,
84
+ "ғ": 79,
85
+ "қ": 80,
86
+ "ң": 81,
87
+ "ү": 82,
88
+ "ұ": 83,
89
+ "һ": 84,
90
+ "ә": 85,
91
+ "ө": 86,
92
+ "٪": 87,
93
+ "–": 88,
94
+ "™": 89,
95
+ "⏳": 90,
96
+ "⚐": 91,
97
+ "⚑": 92,
98
+ "️": 93,
99
+ "﹪": 94,
100
+ "🌍": 95,
101
+ "🌏": 96,
102
+ "🎉": 97,
103
+ "🎭": 98,
104
+ "🎰": 99,
105
+ "🏠": 100,
106
+ "🏢": 101,
107
+ "🏬": 102,
108
+ "🏭": 103,
109
+ "🏳": 104,
110
+ "👅": 105,
111
+ "👑": 106,
112
+ "👤": 107,
113
+ "👽": 108,
114
+ "💯": 109,
115
+ "💲": 110,
116
+ "💼": 111,
117
+ "📆": 112,
118
+ "📈": 113,
119
+ "📖": 114,
120
+ "📝": 115,
121
+ "📞": 116,
122
+ "🔠": 117,
123
+ "🔢": 118,
124
+ "🔤": 119,
125
+ "🕑": 120,
126
+ "😷": 121,
127
+ "🧮": 122,
128
+ "🪶": 123
129
+ }
130
+ }