sanchit-gandhi HF staff commited on
Commit
7682a5f
1 Parent(s): 99f48de

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 +45 -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": "bqi",
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 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 42,
3
+ "|": 0,
4
+ "ء": 39,
5
+ "آ": 28,
6
+ "ئ": 37,
7
+ "ا": 2,
8
+ "ب": 10,
9
+ "ت": 12,
10
+ "ث": 35,
11
+ "ج": 24,
12
+ "ح": 22,
13
+ "خ": 15,
14
+ "د": 14,
15
+ "ذ": 33,
16
+ "ر": 7,
17
+ "ز": 16,
18
+ "س": 8,
19
+ "ش": 18,
20
+ "ص": 31,
21
+ "ض": 34,
22
+ "ط": 29,
23
+ "ظ": 36,
24
+ "ع": 21,
25
+ "غ": 30,
26
+ "ف": 27,
27
+ "ق": 25,
28
+ "ل": 17,
29
+ "م": 6,
30
+ "ن": 5,
31
+ "ه": 4,
32
+ "و": 3,
33
+ "ٚ": 13,
34
+ "ٛ": 32,
35
+ "پ": 20,
36
+ "چ": 26,
37
+ "ژ": 38,
38
+ "ک": 9,
39
+ "گ": 19,
40
+ "ۆ": 40,
41
+ "ی": 1,
42
+ "ێ": 41,
43
+ "ۨ": 23,
44
+ "ݚ": 11
45
+ }