ganga4364 commited on
Commit
9ac981b
1 Parent(s): 3b13508

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 130,
3
+ "<s>": 129
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
+ "127": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "128": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "129": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "130": {
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 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": 47,
3
+ "1": 58,
4
+ "2": 24,
5
+ "3": 0,
6
+ "4": 10,
7
+ "5": 51,
8
+ "6": 22,
9
+ "7": 111,
10
+ "8": 20,
11
+ "9": 8,
12
+ "[PAD]": 128,
13
+ "[UNK]": 127,
14
+ "^": 53,
15
+ "|": 76,
16
+ "~": 118,
17
+ "": 68,
18
+ "«": 18,
19
+ "å": 71,
20
+ "ༀ": 78,
21
+ "་": 115,
22
+ "།": 104,
23
+ "༕": 125,
24
+ "༙": 75,
25
+ "༡": 117,
26
+ "༢": 64,
27
+ "༣": 50,
28
+ "༤": 116,
29
+ "༥": 85,
30
+ "༦": 97,
31
+ "༧": 1,
32
+ "༨": 55,
33
+ "༩": 2,
34
+ "༵": 19,
35
+ "ཀ": 86,
36
+ "ཁ": 11,
37
+ "ག": 112,
38
+ "གྷ": 30,
39
+ "ང": 16,
40
+ "ཅ": 90,
41
+ "ཆ": 77,
42
+ "ཇ": 79,
43
+ "ཉ": 4,
44
+ "ཊ": 23,
45
+ "ཋ": 48,
46
+ "ཌ": 43,
47
+ "ཌྷ": 42,
48
+ "ཎ": 119,
49
+ "ཏ": 109,
50
+ "ཐ": 107,
51
+ "ད": 121,
52
+ "དྷ": 37,
53
+ "ན": 29,
54
+ "པ": 87,
55
+ "ཕ": 59,
56
+ "བ": 33,
57
+ "བྷ": 91,
58
+ "མ": 15,
59
+ "ཙ": 17,
60
+ "ཚ": 46,
61
+ "ཛ": 98,
62
+ "ཝ": 3,
63
+ "ཞ": 14,
64
+ "ཟ": 60,
65
+ "འ": 122,
66
+ "ཡ": 108,
67
+ "ར": 5,
68
+ "ལ": 56,
69
+ "ཤ": 88,
70
+ "ཥ": 41,
71
+ "ས": 120,
72
+ "ཧ": 38,
73
+ "ཨ": 34,
74
+ "ཀྵ": 61,
75
+ "ཪ": 89,
76
+ "ཱ": 81,
77
+ "ི": 63,
78
+ "ཱི": 84,
79
+ "ུ": 67,
80
+ "ཱུ": 27,
81
+ "ཷ": 12,
82
+ "ེ": 94,
83
+ "ོ": 54,
84
+ "ཾ": 99,
85
+ "ྀ": 7,
86
+ "ཱྀ": 114,
87
+ "ྃ": 93,
88
+ "ྐ": 72,
89
+ "ྑ": 57,
90
+ "ྒ": 13,
91
+ "ྔ": 9,
92
+ "ྕ": 103,
93
+ "ྖ": 62,
94
+ "ྗ": 65,
95
+ "ྙ": 113,
96
+ "ྚ": 69,
97
+ "ྛ": 45,
98
+ "ྜ": 100,
99
+ "ྞ": 83,
100
+ "ྟ": 82,
101
+ "ྠ": 44,
102
+ "ྡ": 92,
103
+ "ྡྷ": 106,
104
+ "ྣ": 26,
105
+ "ྤ": 105,
106
+ "ྥ": 36,
107
+ "ྦ": 31,
108
+ "ྦྷ": 101,
109
+ "ྨ": 70,
110
+ "ྩ": 123,
111
+ "ྪ": 39,
112
+ "ྫ": 21,
113
+ "ྭ": 35,
114
+ "ྰ": 74,
115
+ "ྱ": 49,
116
+ "ྲ": 32,
117
+ "ླ": 124,
118
+ "ྴ": 73,
119
+ "ྵ": 52,
120
+ "ྶ": 28,
121
+ "ྷ": 66,
122
+ "ྸ": 40,
123
+ "ྺ": 95,
124
+ "ྻ": 102,
125
+ "ྼ": 25,
126
+ "•": 6,
127
+ "Ⅳ": 80,
128
+ "停": 110,
129
+ "抢": 126,
130
+ "1": 96
131
+ }