sanchit-gandhi HF staff commited on
Commit
853f140
1 Parent(s): ccd1840

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 +44 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "ल",
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": "bgw",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ल",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 14,
3
+ "'": 30,
4
+ "6": 23,
5
+ "_": 41,
6
+ "ं": 13,
7
+ "अ": 33,
8
+ "आ": 38,
9
+ "इ": 2,
10
+ "ई": 8,
11
+ "उ": 25,
12
+ "ऊ": 18,
13
+ "ए": 19,
14
+ "ओ": 28,
15
+ "क": 27,
16
+ "ख": 1,
17
+ "ग": 22,
18
+ "च": 17,
19
+ "ज": 39,
20
+ "ट": 31,
21
+ "ड": 21,
22
+ "त": 11,
23
+ "द": 34,
24
+ "न": 36,
25
+ "प": 40,
26
+ "ब": 10,
27
+ "भ": 26,
28
+ "म": 16,
29
+ "य": 12,
30
+ "र": 4,
31
+ "ल": 0,
32
+ "व": 35,
33
+ "स": 5,
34
+ "ह": 6,
35
+ "़": 32,
36
+ "ा": 3,
37
+ "ि": 7,
38
+ "ी": 9,
39
+ "ु": 24,
40
+ "ू": 20,
41
+ "े": 15,
42
+ "ो": 37,
43
+ "‍": 29
44
+ }