sanchit-gandhi HF staff commited on
Commit
812a816
1 Parent(s): 39be3a7

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 +55 -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": "div",
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 52,
3
+ "'": 43,
4
+ "|": 0,
5
+ "ا": 47,
6
+ "ل": 45,
7
+ "ه": 48,
8
+ "ހ": 14,
9
+ "ށ": 22,
10
+ "ނ": 5,
11
+ "ރ": 13,
12
+ "ބ": 19,
13
+ "ޅ": 25,
14
+ "ކ": 9,
15
+ "އ": 3,
16
+ "ވ": 10,
17
+ "މ": 12,
18
+ "ފ": 18,
19
+ "ދ": 17,
20
+ "ތ": 16,
21
+ "ލ": 21,
22
+ "ގ": 11,
23
+ "ޏ": 37,
24
+ "ސ": 20,
25
+ "ޑ": 27,
26
+ "ޒ": 35,
27
+ "ޓ": 33,
28
+ "ޔ": 26,
29
+ "ޕ": 31,
30
+ "ޖ": 29,
31
+ "ޗ": 38,
32
+ "ޘ": 51,
33
+ "ޙ": 30,
34
+ "ޚ": 39,
35
+ "ޛ": 49,
36
+ "ޝ": 40,
37
+ "ޞ": 41,
38
+ "ޟ": 44,
39
+ "ޠ": 50,
40
+ "ޡ": 46,
41
+ "ޢ": 36,
42
+ "ޣ": 42,
43
+ "ޤ": 34,
44
+ "ަ": 1,
45
+ "ާ": 8,
46
+ "ި": 7,
47
+ "ީ": 15,
48
+ "ު": 6,
49
+ "ޫ": 28,
50
+ "ެ": 2,
51
+ "ޭ": 23,
52
+ "ޮ": 24,
53
+ "ޯ": 32,
54
+ "ް": 4
55
+ }