Hugging Face's logo

roviso
/
riri-small

Model card Files Community
roviso commited on
Commit
da567a3
•
1 Parent(s): 0ac0830

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