hadiqa123 commited on
Commit
a175ebf
1 Parent(s): 9f0f86b

add tokenizer

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