sanchit-gandhi HF staff commited on
Commit
5972c1b
1 Parent(s): 97bd3f1

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +4 -0
  2. tokenizer_config.json +12 -0
  3. vocab.json +66 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "|",
3
+ "unk_token": "<unk>"
4
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "clean_up_tokenization_spaces": true,
4
+ "is_uroman": false,
5
+ "language": "dgo",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "|",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 63,
3
+ "'": 59,
4
+ "-": 49,
5
+ "4": 62,
6
+ "|": 0,
7
+ "ँ": 42,
8
+ "ं": 10,
9
+ "ः": 58,
10
+ "अ": 32,
11
+ "आ": 24,
12
+ "इ": 45,
13
+ "ई": 26,
14
+ "उ": 29,
15
+ "ऊ": 40,
16
+ "ए": 33,
17
+ "ऐ": 31,
18
+ "ओ": 23,
19
+ "औ": 54,
20
+ "क": 5,
21
+ "ख": 28,
22
+ "ग": 17,
23
+ "घ": 55,
24
+ "च": 22,
25
+ "छ": 41,
26
+ "ज": 18,
27
+ "झ": 50,
28
+ "ञ": 56,
29
+ "ट": 39,
30
+ "ठ": 48,
31
+ "ड": 27,
32
+ "ढ": 51,
33
+ "ण": 53,
34
+ "त": 8,
35
+ "थ": 37,
36
+ "द": 6,
37
+ "ध": 47,
38
+ "न": 3,
39
+ "प": 13,
40
+ "फ": 43,
41
+ "ब": 21,
42
+ "भ": 46,
43
+ "म": 14,
44
+ "य": 16,
45
+ "र": 4,
46
+ "ल": 12,
47
+ "व": 35,
48
+ "श": 34,
49
+ "ष": 52,
50
+ "स": 9,
51
+ "ह": 36,
52
+ "़": 30,
53
+ "ा": 2,
54
+ "ि": 15,
55
+ "ी": 7,
56
+ "ु": 20,
57
+ "ू": 38,
58
+ "ृ": 57,
59
+ "े": 1,
60
+ "ै": 19,
61
+ "ॉ": 60,
62
+ "ो": 25,
63
+ "ौ": 44,
64
+ "्": 11,
65
+ "‍": 61
66
+ }