hadiqa123 commited on
Commit
ac7958c
1 Parent(s): 63aaa07

add tokenizer

Browse files
Files changed (1) hide show
  1. vocab.json +43 -43
vocab.json CHANGED
@@ -1,47 +1,47 @@
1
  {
2
- " ": 20,
3
  "PAD": 43,
4
  "[UNK]": 44,
5
- "آ": 1,
6
- "أ": 0,
7
- "ؤ": 18,
8
- "ئ": 29,
9
- "ا": 13,
10
- "ب": 33,
11
- "ت": 25,
12
- "ث": 15,
13
- "ج": 37,
14
- "ح": 17,
15
- "خ": 31,
16
- "د": 12,
17
- "ذ": 24,
18
- "ر": 42,
19
- "ز": 39,
20
- "س": 41,
21
- "ش": 27,
22
- "ص": 21,
23
- "ض": 9,
24
- "ط": 14,
25
- "ظ": 26,
26
- "ع": 35,
27
- "غ": 30,
28
- "ف": 19,
29
- "ق": 34,
30
- "ل": 32,
31
- "م": 16,
32
- "ن": 28,
33
- "و": 40,
34
- "ً": 6,
35
- "ٹ": 5,
36
- "پ": 23,
37
- "چ": 10,
38
- "ڈ": 7,
39
- "ڑ": 4,
40
- "ک": 8,
41
- "گ": 11,
42
- "ں": 36,
43
- "ھ": 3,
44
- "ہ": 2,
45
- "ی": 38,
46
- "ے": 22
47
  }
 
1
  {
2
+ " ": 35,
3
  "PAD": 43,
4
  "[UNK]": 44,
5
+ "آ": 7,
6
+ "أ": 2,
7
+ "ؤ": 27,
8
+ "ئ": 15,
9
+ "ا": 26,
10
+ "ب": 39,
11
+ "ت": 32,
12
+ "ث": 31,
13
+ "ج": 11,
14
+ "ح": 29,
15
+ "خ": 37,
16
+ "د": 23,
17
+ "ذ": 21,
18
+ "ر": 34,
19
+ "ز": 20,
20
+ "س": 18,
21
+ "ش": 33,
22
+ "ص": 42,
23
+ "ض": 5,
24
+ "ط": 9,
25
+ "ظ": 8,
26
+ "ع": 24,
27
+ "غ": 28,
28
+ "ف": 0,
29
+ "ق": 22,
30
+ "ل": 19,
31
+ "م": 4,
32
+ "ن": 3,
33
+ "و": 14,
34
+ "ً": 13,
35
+ "ٹ": 38,
36
+ "پ": 36,
37
+ "چ": 6,
38
+ "ڈ": 17,
39
+ "ڑ": 40,
40
+ "ک": 16,
41
+ "گ": 12,
42
+ "ں": 30,
43
+ "ھ": 25,
44
+ "ہ": 10,
45
+ "ی": 1,
46
+ "ے": 41
47
  }