sanchit-gandhi HF staff commited on
Commit
6c398ed
1 Parent(s): dae467a

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 +63 -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": "hne",
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 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 60,
3
+ "'": 53,
4
+ "-": 46,
5
+ "0": 56,
6
+ "3": 58,
7
+ "4": 55,
8
+ "5": 57,
9
+ "6": 54,
10
+ "|": 0,
11
+ "ं": 12,
12
+ "ः": 51,
13
+ "अ": 19,
14
+ "आ": 33,
15
+ "इ": 31,
16
+ "ई": 35,
17
+ "उ": 45,
18
+ "ऊ": 23,
19
+ "ए": 28,
20
+ "ओ": 24,
21
+ "क": 4,
22
+ "ख": 27,
23
+ "ग": 26,
24
+ "घ": 38,
25
+ "च": 30,
26
+ "छ": 42,
27
+ "ज": 20,
28
+ "झ": 44,
29
+ "ट": 40,
30
+ "ठ": 43,
31
+ "ड": 36,
32
+ "ढ": 48,
33
+ "त": 11,
34
+ "थ": 32,
35
+ "द": 21,
36
+ "ध": 37,
37
+ "न": 5,
38
+ "प": 14,
39
+ "फ": 47,
40
+ "ब": 13,
41
+ "भ": 34,
42
+ "म": 6,
43
+ "य": 15,
44
+ "र": 2,
45
+ "ल": 10,
46
+ "व": 17,
47
+ "स": 8,
48
+ "ह": 7,
49
+ "़": 39,
50
+ "ा": 1,
51
+ "ि": 9,
52
+ "ी": 16,
53
+ "ु": 22,
54
+ "ू": 25,
55
+ "ृ": 59,
56
+ "े": 3,
57
+ "ै": 50,
58
+ "ो": 18,
59
+ "ौ": 49,
60
+ "्": 29,
61
+ "‍": 41,
62
+ "–": 52
63
+ }