sanchit-gandhi HF staff commited on
Commit
02f2908
1 Parent(s): a3d5089

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 +46 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "ل",
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": "fas",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ل",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 30,
3
+ "'": 40,
4
+ "-": 35,
5
+ "_": 6,
6
+ "ء": 14,
7
+ "آ": 34,
8
+ "أ": 3,
9
+ "ؤ": 36,
10
+ "ئ": 4,
11
+ "ا": 41,
12
+ "ب": 26,
13
+ "ت": 25,
14
+ "ث": 20,
15
+ "ج": 8,
16
+ "ح": 18,
17
+ "خ": 32,
18
+ "د": 28,
19
+ "ذ": 5,
20
+ "ر": 9,
21
+ "ز": 43,
22
+ "س": 39,
23
+ "ش": 31,
24
+ "ص": 16,
25
+ "ض": 42,
26
+ "ط": 19,
27
+ "ظ": 24,
28
+ "ع": 2,
29
+ "غ": 29,
30
+ "ف": 11,
31
+ "ق": 17,
32
+ "ك": 7,
33
+ "ل": 0,
34
+ "م": 23,
35
+ "ن": 22,
36
+ "ه": 10,
37
+ "و": 27,
38
+ "ي": 13,
39
+ "ٔ": 21,
40
+ "پ": 1,
41
+ "چ": 37,
42
+ "ژ": 38,
43
+ "ک": 33,
44
+ "گ": 12,
45
+ "ی": 15
46
+ }