Hugging Face's logo

roviso
/
riri-np-small

Model card Files Community
roviso commited on
Commit
16242d5
•
1 Parent(s): abd3b9e

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +22 -0
  3. tokenizer_config.json +13 -0
  4. vocab.json +108 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 105,
3
+ "<s>": 104
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "[PAD]",
21
+ "unk_token": "[UNK]"
22
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "replace_word_delimiter_char": " ",
9
+ "target_lang": "npi",
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "npi": {
3
+ "!": 1,
4
+ "\"": 2,
5
+ "'": 3,
6
+ "(": 4,
7
+ ")": 5,
8
+ ",": 6,
9
+ "-": 7,
10
+ ".": 8,
11
+ "/": 9,
12
+ ":": 10,
13
+ ";": 11,
14
+ "?": 12,
15
+ "M": 13,
16
+ "[PAD]": 103,
17
+ "[UNK]": 102,
18
+ "e": 14,
19
+ "o": 15,
20
+ "r": 16,
21
+ "|": 0,
22
+ "¥": 17,
23
+ "·": 18,
24
+ "÷": 19,
25
+ "ँ": 20,
26
+ "ं": 21,
27
+ "ः": 22,
28
+ "अ": 23,
29
+ "आ": 24,
30
+ "इ": 25,
31
+ "ई": 26,
32
+ "उ": 27,
33
+ "ऊ": 28,
34
+ "ऋ": 29,
35
+ "ए": 30,
36
+ "ऐ": 31,
37
+ "ओ": 32,
38
+ "औ": 33,
39
+ "क": 34,
40
+ "ख": 35,
41
+ "ग": 36,
42
+ "घ": 37,
43
+ "ङ": 38,
44
+ "च": 39,
45
+ "छ": 40,
46
+ "ज": 41,
47
+ "झ": 42,
48
+ "ञ": 43,
49
+ "ट": 44,
50
+ "ठ": 45,
51
+ "ड": 46,
52
+ "ढ": 47,
53
+ "ण": 48,
54
+ "त": 49,
55
+ "थ": 50,
56
+ "द": 51,
57
+ "ध": 52,
58
+ "न": 53,
59
+ "प": 54,
60
+ "फ": 55,
61
+ "ब": 56,
62
+ "भ": 57,
63
+ "म": 58,
64
+ "य": 59,
65
+ "र": 60,
66
+ "ल": 61,
67
+ "व": 62,
68
+ "श": 63,
69
+ "ष": 64,
70
+ "स": 65,
71
+ "ह": 66,
72
+ "़": 67,
73
+ "ा": 68,
74
+ "ि": 69,
75
+ "ी": 70,
76
+ "ु": 71,
77
+ "ू": 72,
78
+ "ृ": 73,
79
+ "े": 74,
80
+ "ै": 75,
81
+ "ो": 76,
82
+ "ौ": 77,
83
+ "्": 78,
84
+ "ॐ": 79,
85
+ "।": 80,
86
+ "०": 81,
87
+ "१": 82,
88
+ "२": 83,
89
+ "३": 84,
90
+ "४": 85,
91
+ "५": 86,
92
+ "६": 87,
93
+ "७": 88,
94
+ "८": 89,
95
+ "९": 90,
96
+ "​": 91,
97
+ "‌": 92,
98
+ "‍": 93,
99
+ "–": 94,
100
+ "—": 95,
101
+ "‘": 96,
102
+ "’": 97,
103
+ "“": 98,
104
+ "”": 99,
105
+ "…": 100,
106
+ " ": 101
107
+ }
108
+ }