Hugging Face's logo

HuyenNguyen
/
wav2vec2-base

Model card Files Community
HuyenNguyen commited on
Commit
9ba62ac
•
1 Parent(s): 1f2f3bf

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +47 -0
  4. vocab.json +99 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 98,
3
+ "<s>": 97
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
+ "95": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "96": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "97": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "98": {
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 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 45,
3
+ "[PAD]": 96,
4
+ "[UNK]": 95,
5
+ "a": 51,
6
+ "b": 3,
7
+ "c": 18,
8
+ "d": 25,
9
+ "e": 54,
10
+ "f": 11,
11
+ "g": 94,
12
+ "h": 5,
13
+ "i": 74,
14
+ "j": 37,
15
+ "k": 7,
16
+ "l": 31,
17
+ "m": 16,
18
+ "n": 21,
19
+ "o": 89,
20
+ "p": 63,
21
+ "q": 34,
22
+ "r": 70,
23
+ "s": 38,
24
+ "t": 82,
25
+ "u": 19,
26
+ "v": 40,
27
+ "w": 39,
28
+ "x": 88,
29
+ "y": 57,
30
+ "z": 26,
31
+ "|": 29,
32
+ "à": 66,
33
+ "á": 44,
34
+ "â": 83,
35
+ "ã": 61,
36
+ "è": 77,
37
+ "é": 93,
38
+ "ê": 30,
39
+ "ì": 56,
40
+ "í": 73,
41
+ "ò": 8,
42
+ "ó": 46,
43
+ "ô": 71,
44
+ "õ": 6,
45
+ "ù": 67,
46
+ "ú": 80,
47
+ "ý": 50,
48
+ "ă": 9,
49
+ "đ": 91,
50
+ "ĩ": 49,
51
+ "ũ": 76,
52
+ "ơ": 84,
53
+ "ư": 24,
54
+ "ạ": 27,
55
+ "ả": 22,
56
+ "ấ": 36,
57
+ "ầ": 12,
58
+ "ẩ": 59,
59
+ "ẫ": 2,
60
+ "ậ": 79,
61
+ "ắ": 42,
62
+ "ằ": 28,
63
+ "ẳ": 55,
64
+ "ẵ": 33,
65
+ "ặ": 52,
66
+ "ẹ": 35,
67
+ "ẻ": 13,
68
+ "ẽ": 41,
69
+ "ế": 65,
70
+ "ề": 4,
71
+ "ể": 15,
72
+ "ễ": 86,
73
+ "ệ": 58,
74
+ "ỉ": 90,
75
+ "ị": 64,
76
+ "ọ": 10,
77
+ "ỏ": 68,
78
+ "ố": 23,
79
+ "ồ": 47,
80
+ "ổ": 81,
81
+ "ỗ": 1,
82
+ "ộ": 14,
83
+ "ớ": 60,
84
+ "ờ": 17,
85
+ "ở": 20,
86
+ "ỡ": 75,
87
+ "ợ": 43,
88
+ "ụ": 69,
89
+ "ủ": 78,
90
+ "ứ": 62,
91
+ "ừ": 0,
92
+ "ử": 72,
93
+ "ữ": 87,
94
+ "ự": 53,
95
+ "ỳ": 32,
96
+ "ỵ": 92,
97
+ "ỷ": 85,
98
+ "ỹ": 48
99
+ }