sanchit-gandhi HF staff commited on
Commit
fba08d4
1 Parent(s): 23a0dc1

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 +74 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "फ",
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": "hin",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "फ",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 7,
3
+ "'": 44,
4
+ "-": 3,
5
+ "0": 8,
6
+ "1": 2,
7
+ "2": 18,
8
+ "3": 25,
9
+ "4": 1,
10
+ "8": 6,
11
+ "_": 33,
12
+ "`": 45,
13
+ "ँ": 16,
14
+ "ं": 30,
15
+ "ः": 35,
16
+ "अ": 4,
17
+ "आ": 55,
18
+ "इ": 5,
19
+ "ई": 34,
20
+ "उ": 32,
21
+ "ऊ": 65,
22
+ "ए": 11,
23
+ "ऐ": 12,
24
+ "ऑ": 19,
25
+ "ओ": 67,
26
+ "औ": 60,
27
+ "क": 70,
28
+ "ख": 42,
29
+ "ग": 49,
30
+ "घ": 47,
31
+ "च": 17,
32
+ "छ": 9,
33
+ "ज": 57,
34
+ "झ": 58,
35
+ "ञ": 26,
36
+ "ट": 68,
37
+ "ठ": 29,
38
+ "ड": 56,
39
+ "ढ": 50,
40
+ "ण": 43,
41
+ "त": 69,
42
+ "थ": 20,
43
+ "द": 62,
44
+ "ध": 37,
45
+ "न": 10,
46
+ "प": 48,
47
+ "फ": 0,
48
+ "ब": 41,
49
+ "भ": 21,
50
+ "म": 71,
51
+ "य": 51,
52
+ "र": 39,
53
+ "ल": 38,
54
+ "व": 46,
55
+ "श": 59,
56
+ "ष": 14,
57
+ "स": 40,
58
+ "ह": 36,
59
+ "़": 13,
60
+ "ा": 54,
61
+ "ि": 15,
62
+ "ी": 22,
63
+ "ु": 28,
64
+ "ू": 66,
65
+ "ृ": 63,
66
+ "ॅ": 24,
67
+ "े": 52,
68
+ "ै": 27,
69
+ "ॉ": 31,
70
+ "ो": 61,
71
+ "ौ": 64,
72
+ "्": 53,
73
+ "‍": 23
74
+ }