HuyenNguyen commited on
Commit
d9cf19e
1 Parent(s): 26fe019

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": "tur",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tur": {
3
+ "[PAD]": 88,
4
+ "[UNK]": 87,
5
+ "a": 1,
6
+ "b": 2,
7
+ "c": 3,
8
+ "d": 4,
9
+ "e": 5,
10
+ "g": 6,
11
+ "h": 7,
12
+ "i": 8,
13
+ "k": 9,
14
+ "l": 10,
15
+ "m": 11,
16
+ "n": 12,
17
+ "o": 13,
18
+ "p": 14,
19
+ "q": 15,
20
+ "r": 16,
21
+ "s": 17,
22
+ "t": 18,
23
+ "u": 19,
24
+ "v": 20,
25
+ "x": 21,
26
+ "y": 22,
27
+ "|": 0,
28
+ "à": 23,
29
+ "á": 24,
30
+ "ã": 25,
31
+ "è": 26,
32
+ "é": 27,
33
+ "ê": 28,
34
+ "ì": 29,
35
+ "í": 30,
36
+ "ò": 31,
37
+ "ó": 32,
38
+ "õ": 33,
39
+ "ù": 34,
40
+ "ú": 35,
41
+ "ý": 36,
42
+ "ă": 37,
43
+ "đ": 38,
44
+ "ĩ": 39,
45
+ "ũ": 40,
46
+ "ơ": 41,
47
+ "ư": 42,
48
+ "ạ": 43,
49
+ "ả": 44,
50
+ "ấ": 45,
51
+ "ầ": 46,
52
+ "ẩ": 47,
53
+ "ẫ": 48,
54
+ "ậ": 49,
55
+ "ắ": 50,
56
+ "ằ": 51,
57
+ "ẳ": 52,
58
+ "ẵ": 53,
59
+ "ặ": 54,
60
+ "ẹ": 55,
61
+ "ẻ": 56,
62
+ "ẽ": 57,
63
+ "ế": 58,
64
+ "ề": 59,
65
+ "ể": 60,
66
+ "ễ": 61,
67
+ "ệ": 62,
68
+ "ỉ": 63,
69
+ "ị": 64,
70
+ "ọ": 65,
71
+ "ỏ": 66,
72
+ "ố": 67,
73
+ "ồ": 68,
74
+ "ổ": 69,
75
+ "ỗ": 70,
76
+ "ộ": 71,
77
+ "ớ": 72,
78
+ "ờ": 73,
79
+ "ở": 74,
80
+ "ỡ": 75,
81
+ "ợ": 76,
82
+ "ụ": 77,
83
+ "ủ": 78,
84
+ "ứ": 79,
85
+ "ừ": 80,
86
+ "ử": 81,
87
+ "ữ": 82,
88
+ "ự": 83,
89
+ "ỳ": 84,
90
+ "ỷ": 85,
91
+ "ỹ": 86
92
+ }
93
+ }