spsither commited on
Commit
bc9548d
1 Parent(s): 3670ec5

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 114,
3
+ "<s>": 113
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 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<s>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ ],
32
+ "bos_token": "<s>",
33
+ "eos_token": "</s>",
34
+ "pad_token": "[PAD]",
35
+ "unk_token": "[UNK]"
36
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "processor_class": "Wav2Vec2Processor",
9
+ "replace_word_delimiter_char": " ",
10
+ "target_lang": null,
11
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
12
+ "unk_token": "[UNK]",
13
+ "word_delimiter_token": "|"
14
+ }
vocab.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 76,
3
+ "[PAD]": 112,
4
+ "[UNK]": 111,
5
+ "|": 34,
6
+ "ༀ": 75,
7
+ "་": 94,
8
+ "༌": 95,
9
+ "༔": 37,
10
+ "༡": 45,
11
+ "༢": 97,
12
+ "༣": 15,
13
+ "༤": 100,
14
+ "༥": 98,
15
+ "༦": 74,
16
+ "༧": 92,
17
+ "༨": 110,
18
+ "༩": 83,
19
+ "༷": 54,
20
+ "༸": 105,
21
+ "ཀ": 19,
22
+ "ཁ": 71,
23
+ "ག": 72,
24
+ "གྷ": 68,
25
+ "ང": 25,
26
+ "ཅ": 99,
27
+ "ཆ": 29,
28
+ "ཇ": 46,
29
+ "ཉ": 42,
30
+ "ཊ": 13,
31
+ "ཋ": 108,
32
+ "ཌ": 28,
33
+ "ཌྷ": 47,
34
+ "ཎ": 17,
35
+ "ཏ": 33,
36
+ "ཐ": 58,
37
+ "ད": 107,
38
+ "དྷ": 102,
39
+ "ན": 51,
40
+ "པ": 14,
41
+ "ཕ": 73,
42
+ "བ": 93,
43
+ "བྷ": 61,
44
+ "མ": 27,
45
+ "ཙ": 59,
46
+ "ཚ": 84,
47
+ "ཛ": 24,
48
+ "ཝ": 77,
49
+ "ཞ": 41,
50
+ "ཟ": 20,
51
+ "འ": 49,
52
+ "ཡ": 52,
53
+ "ར": 16,
54
+ "ལ": 60,
55
+ "ཤ": 62,
56
+ "ཥ": 43,
57
+ "ས": 53,
58
+ "ཧ": 12,
59
+ "ཨ": 7,
60
+ "ཀྵ": 64,
61
+ "ཪ": 8,
62
+ "ཱ": 48,
63
+ "ི": 21,
64
+ "ཱི": 50,
65
+ "ུ": 82,
66
+ "ཱུ": 90,
67
+ "ེ": 80,
68
+ "ཻ": 86,
69
+ "ོ": 70,
70
+ "ཽ": 89,
71
+ "ཾ": 22,
72
+ "ཿ": 96,
73
+ "ྀ": 87,
74
+ "ཱྀ": 26,
75
+ "ྂ": 85,
76
+ "ྃ": 10,
77
+ "྄": 44,
78
+ "྅": 38,
79
+ "ྐ": 106,
80
+ "ྑ": 88,
81
+ "ྒ": 5,
82
+ "ྔ": 11,
83
+ "ྕ": 104,
84
+ "ྖ": 79,
85
+ "ྗ": 3,
86
+ "ྙ": 67,
87
+ "ྚ": 63,
88
+ "ྛ": 0,
89
+ "ྜ": 65,
90
+ "ྞ": 18,
91
+ "ྟ": 2,
92
+ "ྠ": 6,
93
+ "ྡ": 31,
94
+ "ྡྷ": 32,
95
+ "ྣ": 1,
96
+ "ྤ": 103,
97
+ "ྥ": 39,
98
+ "ྦ": 9,
99
+ "ྦྷ": 66,
100
+ "ྨ": 23,
101
+ "ྩ": 78,
102
+ "ྪ": 35,
103
+ "ྫ": 91,
104
+ "ྭ": 56,
105
+ "ྰ": 101,
106
+ "ྱ": 30,
107
+ "ྲ": 4,
108
+ "ླ": 55,
109
+ "ྴ": 36,
110
+ "ྵ": 57,
111
+ "ྶ": 109,
112
+ "ྷ": 81,
113
+ "ྸ": 40,
114
+ "ྻ": 69
115
+ }