snu-nia-12 commited on
Commit
d335a69
โ€ข
1 Parent(s): 5abca60
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
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 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "pad_token": "[PAD]",
6
+ "processor_class": "Wav2Vec2Processor",
7
+ "replace_word_delimiter_char": " ",
8
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
9
+ "unk_token": "[UNK]",
10
+ "word_delimiter_token": "|"
11
+ }
vocab.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": 1,
3
+ "1": 2,
4
+ "2": 3,
5
+ "3": 4,
6
+ "4": 5,
7
+ "5": 6,
8
+ "6": 7,
9
+ "7": 8,
10
+ "8": 9,
11
+ "9": 10,
12
+ "[PAD]": 126,
13
+ "[UNK]": 125,
14
+ "a": 11,
15
+ "b": 12,
16
+ "c": 13,
17
+ "d": 14,
18
+ "e": 15,
19
+ "f": 16,
20
+ "g": 17,
21
+ "h": 18,
22
+ "i": 19,
23
+ "j": 20,
24
+ "k": 21,
25
+ "l": 22,
26
+ "m": 23,
27
+ "n": 24,
28
+ "o": 25,
29
+ "p": 26,
30
+ "q": 27,
31
+ "r": 28,
32
+ "s": 29,
33
+ "t": 30,
34
+ "u": 31,
35
+ "v": 32,
36
+ "w": 33,
37
+ "x": 34,
38
+ "y": 35,
39
+ "z": 36,
40
+ "|": 0,
41
+ "ฮฑ": 37,
42
+ "ฮผ": 38,
43
+ "ใ€…": 39,
44
+ "ใ€‡": 40,
45
+ "ใ": 41,
46
+ "ใ‚": 42,
47
+ "ใƒ": 43,
48
+ "ใ„": 44,
49
+ "ใ…": 45,
50
+ "ใ†": 46,
51
+ "ใ‡": 47,
52
+ "ใˆ": 48,
53
+ "ใ‰": 49,
54
+ "ใŠ": 50,
55
+ "ใ‹": 51,
56
+ "ใŒ": 52,
57
+ "ใ": 53,
58
+ "ใŽ": 54,
59
+ "ใ": 55,
60
+ "ใ": 56,
61
+ "ใ‘": 57,
62
+ "ใ’": 58,
63
+ "ใ“": 59,
64
+ "ใ”": 60,
65
+ "ใ•": 61,
66
+ "ใ–": 62,
67
+ "ใ—": 63,
68
+ "ใ˜": 64,
69
+ "ใ™": 65,
70
+ "ใš": 66,
71
+ "ใ›": 67,
72
+ "ใœ": 68,
73
+ "ใ": 69,
74
+ "ใž": 70,
75
+ "ใŸ": 71,
76
+ "ใ ": 72,
77
+ "ใก": 73,
78
+ "ใข": 74,
79
+ "ใฃ": 75,
80
+ "ใค": 76,
81
+ "ใฅ": 77,
82
+ "ใฆ": 78,
83
+ "ใง": 79,
84
+ "ใจ": 80,
85
+ "ใฉ": 81,
86
+ "ใช": 82,
87
+ "ใซ": 83,
88
+ "ใฌ": 84,
89
+ "ใญ": 85,
90
+ "ใฎ": 86,
91
+ "ใฏ": 87,
92
+ "ใฐ": 88,
93
+ "ใฑ": 89,
94
+ "ใฒ": 90,
95
+ "ใณ": 91,
96
+ "ใด": 92,
97
+ "ใต": 93,
98
+ "ใถ": 94,
99
+ "ใท": 95,
100
+ "ใธ": 96,
101
+ "ใน": 97,
102
+ "ใบ": 98,
103
+ "ใป": 99,
104
+ "ใผ": 100,
105
+ "ใฝ": 101,
106
+ "ใพ": 102,
107
+ "ใฟ": 103,
108
+ "ใ‚€": 104,
109
+ "ใ‚": 105,
110
+ "ใ‚‚": 106,
111
+ "ใ‚ƒ": 107,
112
+ "ใ‚„": 108,
113
+ "ใ‚…": 109,
114
+ "ใ‚†": 110,
115
+ "ใ‚‡": 111,
116
+ "ใ‚ˆ": 112,
117
+ "ใ‚‰": 113,
118
+ "ใ‚Š": 114,
119
+ "ใ‚‹": 115,
120
+ "ใ‚Œ": 116,
121
+ "ใ‚": 117,
122
+ "ใ‚": 118,
123
+ "ใ‚’": 119,
124
+ "ใ‚“": 120,
125
+ "ใ‚”": 121,
126
+ "ใ‚•": 122,
127
+ "ใ‚–": 123,
128
+ "ใƒผ": 124
129
+ }