ducha07 commited on
Commit
b0ed1a1
1 Parent(s): 37b1eb3

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 109,
3
+ "<s>": 108
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "106": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "107": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "108": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "109": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": "vie",
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vie": {
3
+ "/": 1,
4
+ "0": 2,
5
+ "1": 3,
6
+ "2": 4,
7
+ "3": 5,
8
+ "4": 6,
9
+ "5": 7,
10
+ "6": 8,
11
+ "7": 9,
12
+ "8": 10,
13
+ "9": 11,
14
+ "[": 12,
15
+ "[PAD]": 107,
16
+ "[UNK]": 106,
17
+ "]": 13,
18
+ "a": 14,
19
+ "b": 15,
20
+ "c": 16,
21
+ "d": 17,
22
+ "e": 18,
23
+ "f": 19,
24
+ "g": 20,
25
+ "h": 21,
26
+ "i": 22,
27
+ "j": 23,
28
+ "k": 24,
29
+ "l": 25,
30
+ "m": 26,
31
+ "n": 27,
32
+ "o": 28,
33
+ "p": 29,
34
+ "q": 30,
35
+ "r": 31,
36
+ "s": 32,
37
+ "t": 33,
38
+ "u": 34,
39
+ "v": 35,
40
+ "w": 36,
41
+ "x": 37,
42
+ "y": 38,
43
+ "|": 0,
44
+ "à": 39,
45
+ "á": 40,
46
+ "â": 41,
47
+ "ã": 42,
48
+ "è": 43,
49
+ "é": 44,
50
+ "ê": 45,
51
+ "ì": 46,
52
+ "í": 47,
53
+ "ò": 48,
54
+ "ó": 49,
55
+ "ô": 50,
56
+ "õ": 51,
57
+ "ù": 52,
58
+ "ú": 53,
59
+ "ý": 54,
60
+ "ă": 55,
61
+ "đ": 56,
62
+ "ĩ": 57,
63
+ "ũ": 58,
64
+ "ơ": 59,
65
+ "ư": 60,
66
+ "ạ": 61,
67
+ "ả": 62,
68
+ "ấ": 63,
69
+ "ầ": 64,
70
+ "ẩ": 65,
71
+ "ẫ": 66,
72
+ "ậ": 67,
73
+ "ắ": 68,
74
+ "ằ": 69,
75
+ "ẳ": 70,
76
+ "ẵ": 71,
77
+ "ặ": 72,
78
+ "ẹ": 73,
79
+ "ẻ": 74,
80
+ "ẽ": 75,
81
+ "ế": 76,
82
+ "ề": 77,
83
+ "ể": 78,
84
+ "ễ": 79,
85
+ "ệ": 80,
86
+ "ỉ": 81,
87
+ "ị": 82,
88
+ "ọ": 83,
89
+ "ỏ": 84,
90
+ "ố": 85,
91
+ "ồ": 86,
92
+ "ổ": 87,
93
+ "ỗ": 88,
94
+ "ộ": 89,
95
+ "ớ": 90,
96
+ "ờ": 91,
97
+ "ở": 92,
98
+ "ỡ": 93,
99
+ "ợ": 94,
100
+ "ụ": 95,
101
+ "ủ": 96,
102
+ "ứ": 97,
103
+ "ừ": 98,
104
+ "ử": 99,
105
+ "ữ": 100,
106
+ "ự": 101,
107
+ "ỳ": 102,
108
+ "ỵ": 103,
109
+ "ỷ": 104,
110
+ "ỹ": 105
111
+ }
112
+ }