sanchit-gandhi HF staff commited on
Commit
8a4e813
1 Parent(s): 23a0dc1

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 +60 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "د",
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": "urd-script_arabic",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "د",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 26,
3
+ "'": 4,
4
+ "0": 48,
5
+ "1": 36,
6
+ "2": 24,
7
+ "3": 20,
8
+ "4": 35,
9
+ "5": 8,
10
+ "6": 51,
11
+ "7": 27,
12
+ "8": 7,
13
+ "9": 23,
14
+ "_": 30,
15
+ "آ": 2,
16
+ "أ": 12,
17
+ "ؤ": 3,
18
+ "ئ": 25,
19
+ "ا": 15,
20
+ "ب": 31,
21
+ "ت": 28,
22
+ "ث": 16,
23
+ "ج": 49,
24
+ "ح": 54,
25
+ "خ": 1,
26
+ "د": 0,
27
+ "ذ": 47,
28
+ "ر": 22,
29
+ "ز": 44,
30
+ "س": 57,
31
+ "ش": 34,
32
+ "ص": 19,
33
+ "ض": 42,
34
+ "ط": 6,
35
+ "ظ": 32,
36
+ "ع": 38,
37
+ "غ": 37,
38
+ "ف": 29,
39
+ "ق": 17,
40
+ "ل": 13,
41
+ "م": 40,
42
+ "ن": 9,
43
+ "و": 10,
44
+ "ٰ": 39,
45
+ "ٹ": 46,
46
+ "پ": 52,
47
+ "چ": 5,
48
+ "ڈ": 55,
49
+ "ڑ": 21,
50
+ "ژ": 43,
51
+ "ک": 45,
52
+ "گ": 14,
53
+ "ں": 56,
54
+ "ھ": 41,
55
+ "ہ": 53,
56
+ "ۂ": 50,
57
+ "ی": 18,
58
+ "ے": 11,
59
+ "—": 33
60
+ }