sanchit-gandhi HF staff commited on
Commit
51816fe
1 Parent(s): b333afe

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 +61 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "ཤ",
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": "adx",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ཤ",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 5,
3
+ "_": 19,
4
+ "་": 58,
5
+ "ཀ": 52,
6
+ "ཁ": 13,
7
+ "ག": 51,
8
+ "ང": 32,
9
+ "ཅ": 45,
10
+ "ཆ": 21,
11
+ "ཇ": 39,
12
+ "ཉ": 26,
13
+ "ཊ": 28,
14
+ "ཏ": 29,
15
+ "ཐ": 54,
16
+ "ད": 12,
17
+ "ན": 25,
18
+ "པ": 7,
19
+ "ཕ": 55,
20
+ "བ": 44,
21
+ "མ": 22,
22
+ "ཙ": 11,
23
+ "ཚ": 36,
24
+ "ཛ": 27,
25
+ "ཝ": 48,
26
+ "ཞ": 4,
27
+ "ཟ": 34,
28
+ "འ": 3,
29
+ "ཡ": 49,
30
+ "ར": 53,
31
+ "ལ": 57,
32
+ "ཤ": 0,
33
+ "ས": 35,
34
+ "ཧ": 46,
35
+ "ཨ": 41,
36
+ "ཪ": 33,
37
+ "ཱ": 50,
38
+ "ི": 2,
39
+ "ུ": 16,
40
+ "ེ": 17,
41
+ "ོ": 18,
42
+ "ྐ": 1,
43
+ "ྒ": 43,
44
+ "ྔ": 14,
45
+ "ྕ": 56,
46
+ "ྗ": 40,
47
+ "ྙ": 42,
48
+ "ྟ": 23,
49
+ "ྡ": 20,
50
+ "ྣ": 37,
51
+ "ྤ": 24,
52
+ "ྦ": 30,
53
+ "ྨ": 31,
54
+ "ྩ": 6,
55
+ "ྫ": 8,
56
+ "ྭ": 10,
57
+ "ྱ": 9,
58
+ "ྲ": 47,
59
+ "ླ": 38,
60
+ "ྷ": 15
61
+ }