TKU410410103 commited on
Commit
39e32c8
1 Parent(s): 947aeca

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 123,
3
+ "<s>": 122
4
+ }
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "120": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "121": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "122": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "123": {
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
+ "processor_class": "Wav2Vec2Processor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "[UNK]",
47
+ "word_delimiter_token": "|"
48
+ }
vocab.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "-": 1,
3
+ "0": 2,
4
+ "1": 3,
5
+ "2": 4,
6
+ "3": 5,
7
+ "4": 6,
8
+ "5": 7,
9
+ "6": 8,
10
+ "7": 9,
11
+ "8": 10,
12
+ "9": 11,
13
+ "[PAD]": 121,
14
+ "[UNK]": 120,
15
+ "a": 12,
16
+ "c": 13,
17
+ "f": 14,
18
+ "h": 15,
19
+ "o": 16,
20
+ "p": 17,
21
+ "u": 18,
22
+ "|": 0,
23
+ "々": 19,
24
+ "〇": 20,
25
+ "ぁ": 21,
26
+ "あ": 22,
27
+ "ぃ": 23,
28
+ "い": 24,
29
+ "ぅ": 25,
30
+ "う": 26,
31
+ "ぇ": 27,
32
+ "え": 28,
33
+ "ぉ": 29,
34
+ "お": 30,
35
+ "か": 31,
36
+ "が": 32,
37
+ "き": 33,
38
+ "ぎ": 34,
39
+ "く": 35,
40
+ "ぐ": 36,
41
+ "け": 37,
42
+ "げ": 38,
43
+ "こ": 39,
44
+ "ご": 40,
45
+ "さ": 41,
46
+ "ざ": 42,
47
+ "し": 43,
48
+ "じ": 44,
49
+ "す": 45,
50
+ "ず": 46,
51
+ "せ": 47,
52
+ "ぜ": 48,
53
+ "そ": 49,
54
+ "ぞ": 50,
55
+ "た": 51,
56
+ "だ": 52,
57
+ "ち": 53,
58
+ "ぢ": 54,
59
+ "っ": 55,
60
+ "つ": 56,
61
+ "づ": 57,
62
+ "て": 58,
63
+ "で": 59,
64
+ "と": 60,
65
+ "ど": 61,
66
+ "な": 62,
67
+ "に": 63,
68
+ "ぬ": 64,
69
+ "ね": 65,
70
+ "の": 66,
71
+ "は": 67,
72
+ "ば": 68,
73
+ "ぱ": 69,
74
+ "ひ": 70,
75
+ "び": 71,
76
+ "ぴ": 72,
77
+ "ふ": 73,
78
+ "ぶ": 74,
79
+ "ぷ": 75,
80
+ "へ": 76,
81
+ "べ": 77,
82
+ "ぺ": 78,
83
+ "ほ": 79,
84
+ "ぼ": 80,
85
+ "ぽ": 81,
86
+ "ま": 82,
87
+ "み": 83,
88
+ "む": 84,
89
+ "め": 85,
90
+ "も": 86,
91
+ "ゃ": 87,
92
+ "や": 88,
93
+ "ゅ": 89,
94
+ "ゆ": 90,
95
+ "ょ": 91,
96
+ "よ": 92,
97
+ "ら": 93,
98
+ "り": 94,
99
+ "る": 95,
100
+ "れ": 96,
101
+ "ろ": 97,
102
+ "わ": 98,
103
+ "を": 99,
104
+ "ん": 100,
105
+ "ゔ": 101,
106
+ "ゖ": 102,
107
+ "ー": 103,
108
+ "%": 104,
109
+ "0": 105,
110
+ "1": 106,
111
+ "2": 107,
112
+ "3": 108,
113
+ "4": 109,
114
+ "5": 110,
115
+ "6": 111,
116
+ "7": 112,
117
+ "8": 113,
118
+ "9": 114,
119
+ "D": 115,
120
+ "G": 116,
121
+ "P": 117,
122
+ "i": 118,
123
+ "x": 119
124
+ }