hadiqa123 commited on
Commit
6b77a93
1 Parent(s): 415a603

add tokenizer

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