adkhamboy commited on
Commit
b672dca
1 Parent(s): 5c4a163

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 +12 -0
  4. vocab.json +105 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 103,
3
+ "<s>": 102
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 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "./",
6
+ "pad_token": "[PAD]",
7
+ "replace_word_delimiter_char": " ",
8
+ "special_tokens_map_file": null,
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "&": 1,
3
+ "[PAD]": 102,
4
+ "[UNK]": 101,
5
+ "\\": 2,
6
+ "_": 3,
7
+ "`": 4,
8
+ "a": 5,
9
+ "b": 6,
10
+ "c": 7,
11
+ "d": 8,
12
+ "e": 9,
13
+ "f": 10,
14
+ "g": 11,
15
+ "h": 12,
16
+ "i": 13,
17
+ "j": 14,
18
+ "k": 15,
19
+ "l": 16,
20
+ "m": 17,
21
+ "n": 18,
22
+ "o": 19,
23
+ "p": 20,
24
+ "q": 21,
25
+ "r": 22,
26
+ "s": 23,
27
+ "t": 24,
28
+ "u": 25,
29
+ "v": 26,
30
+ "w": 27,
31
+ "x": 28,
32
+ "y": 29,
33
+ "z": 30,
34
+ "|": 0,
35
+ "©": 32,
36
+ "«": 33,
37
+ "¬": 34,
38
+ "´": 35,
39
+ "µ": 36,
40
+ "»": 37,
41
+ "ë": 38,
42
+ "ò": 39,
43
+ "ó": 40,
44
+ "õ": 41,
45
+ "ü": 42,
46
+ "ģ": 43,
47
+ "ı": 44,
48
+ "ş": 45,
49
+ "ƣ": 46,
50
+ "ƶ": 47,
51
+ "ʙ": 48,
52
+ "ʻ": 49,
53
+ "ʼ": 50,
54
+ "а": 51,
55
+ "б": 52,
56
+ "в": 53,
57
+ "г": 54,
58
+ "д": 55,
59
+ "е": 56,
60
+ "ж": 57,
61
+ "з": 58,
62
+ "и": 59,
63
+ "й": 60,
64
+ "к": 61,
65
+ "л": 62,
66
+ "м": 63,
67
+ "н": 64,
68
+ "о": 65,
69
+ "п": 66,
70
+ "р": 67,
71
+ "с": 68,
72
+ "т": 69,
73
+ "у": 70,
74
+ "ф": 71,
75
+ "х": 72,
76
+ "ч": 73,
77
+ "ш": 74,
78
+ "ъ": 75,
79
+ "ы": 76,
80
+ "ь": 77,
81
+ "э": 78,
82
+ "ю": 79,
83
+ "ё": 80,
84
+ "ј": 81,
85
+ "ў": 82,
86
+ "ғ": 83,
87
+ "қ": 84,
88
+ "ҳ": 85,
89
+ "ӯ": 86,
90
+ "ֹ": 87,
91
+ "‒": 88,
92
+ "–": 89,
93
+ "—": 90,
94
+ "―": 91,
95
+ "’": 92,
96
+ "„": 93,
97
+ "•": 94,
98
+ "…": 95,
99
+ "−": 96,
100
+ "☺": 97,
101
+ "♂": 98,
102
+ "✅": 99,
103
+ "✔": 100,
104
+ "️": 101
105
+ }