sanchit-gandhi commited on
Commit
8906d74
·
1 Parent(s): e229b98

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