sanchit-gandhi HF staff commited on
Commit
ef7d7ed
1 Parent(s): 56717e5

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": "ى",
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": "uig-script_arabic",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ى",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 40,
3
+ "-": 31,
4
+ "0": 34,
5
+ "1": 35,
6
+ "2": 36,
7
+ "4": 39,
8
+ "5": 38,
9
+ "6": 37,
10
+ "|": 1,
11
+ "ئ": 9,
12
+ "ا": 2,
13
+ "ب": 14,
14
+ "ت": 10,
15
+ "ج": 32,
16
+ "خ": 28,
17
+ "د": 8,
18
+ "ر": 6,
19
+ "ز": 22,
20
+ "س": 15,
21
+ "ش": 17,
22
+ "غ": 19,
23
+ "ف": 33,
24
+ "ق": 11,
25
+ "ك": 16,
26
+ "ل": 4,
27
+ "م": 12,
28
+ "ن": 5,
29
+ "و": 24,
30
+ "ى": 0,
31
+ "ي": 13,
32
+ "پ": 20,
33
+ "چ": 26,
34
+ "ڭ": 18,
35
+ "گ": 27,
36
+ "ھ": 25,
37
+ "ۆ": 30,
38
+ "ۇ": 7,
39
+ "ۈ": 23,
40
+ "ۋ": 29,
41
+ "ې": 21,
42
+ "ە": 3
43
+ }