daila commited on
Commit
e9e18d2
1 Parent(s): 0106519

Upload tokenizer

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