DDogeeee commited on
Commit
2e11a1c
1 Parent(s): fe19909

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 90,
3
+ "<s>": 89
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": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 88,
3
+ "[UNK]": 87,
4
+ "a": 1,
5
+ "b": 2,
6
+ "c": 3,
7
+ "d": 4,
8
+ "e": 5,
9
+ "g": 6,
10
+ "h": 7,
11
+ "i": 8,
12
+ "k": 9,
13
+ "l": 10,
14
+ "m": 11,
15
+ "n": 12,
16
+ "o": 13,
17
+ "p": 14,
18
+ "q": 15,
19
+ "r": 16,
20
+ "s": 17,
21
+ "t": 18,
22
+ "u": 19,
23
+ "v": 20,
24
+ "x": 21,
25
+ "y": 22,
26
+ "|": 0,
27
+ "à": 23,
28
+ "á": 24,
29
+ "ã": 25,
30
+ "è": 26,
31
+ "é": 27,
32
+ "ê": 28,
33
+ "ì": 29,
34
+ "í": 30,
35
+ "ò": 31,
36
+ "ó": 32,
37
+ "õ": 33,
38
+ "ù": 34,
39
+ "ú": 35,
40
+ "ý": 36,
41
+ "ă": 37,
42
+ "đ": 38,
43
+ "ĩ": 39,
44
+ "ũ": 40,
45
+ "ơ": 41,
46
+ "ư": 42,
47
+ "ạ": 43,
48
+ "ả": 44,
49
+ "ấ": 45,
50
+ "ầ": 46,
51
+ "ẩ": 47,
52
+ "ẫ": 48,
53
+ "ậ": 49,
54
+ "ắ": 50,
55
+ "ằ": 51,
56
+ "ẳ": 52,
57
+ "ẵ": 53,
58
+ "ặ": 54,
59
+ "ẹ": 55,
60
+ "ẻ": 56,
61
+ "ẽ": 57,
62
+ "ế": 58,
63
+ "ề": 59,
64
+ "ể": 60,
65
+ "ễ": 61,
66
+ "ệ": 62,
67
+ "ỉ": 63,
68
+ "ị": 64,
69
+ "ọ": 65,
70
+ "ỏ": 66,
71
+ "ố": 67,
72
+ "ồ": 68,
73
+ "ổ": 69,
74
+ "ỗ": 70,
75
+ "ộ": 71,
76
+ "ớ": 72,
77
+ "ờ": 73,
78
+ "ở": 74,
79
+ "ỡ": 75,
80
+ "ợ": 76,
81
+ "ụ": 77,
82
+ "ủ": 78,
83
+ "ứ": 79,
84
+ "ừ": 80,
85
+ "ử": 81,
86
+ "ữ": 82,
87
+ "ự": 83,
88
+ "ỳ": 84,
89
+ "ỷ": 85,
90
+ "ỹ": 86
91
+ }