Arbi-Houssem commited on
Commit
d6df79e
1 Parent(s): ed3d68a

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 39
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "ا",
3
+ "unk_token": "<unk>"
4
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "ا",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "39": {
13
+ "content": "<unk>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "clean_up_tokenization_spaces": true,
22
+ "is_uroman": false,
23
+ "language": "ara",
24
+ "model_max_length": 1000000000000000019884624838656,
25
+ "normalize": true,
26
+ "pad_token": "ا",
27
+ "phonemize": false,
28
+ "tokenizer_class": "VitsTokenizer",
29
+ "unk_token": "<unk>",
30
+ "verbose": false
31
+ }
vocab.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 25,
3
+ "_": 37,
4
+ "ء": 26,
5
+ "آ": 27,
6
+ "أ": 20,
7
+ "ؤ": 35,
8
+ "إ": 4,
9
+ "ئ": 38,
10
+ "ا": 0,
11
+ "ب": 28,
12
+ "ة": 7,
13
+ "ت": 12,
14
+ "ث": 19,
15
+ "ج": 13,
16
+ "ح": 23,
17
+ "خ": 11,
18
+ "د": 16,
19
+ "ذ": 6,
20
+ "ر": 9,
21
+ "ز": 34,
22
+ "س": 8,
23
+ "ش": 32,
24
+ "ص": 18,
25
+ "ض": 22,
26
+ "ط": 10,
27
+ "ظ": 14,
28
+ "ع": 3,
29
+ "غ": 5,
30
+ "ف": 36,
31
+ "ق": 33,
32
+ "ك": 2,
33
+ "ل": 31,
34
+ "م": 30,
35
+ "ن": 1,
36
+ "ه": 24,
37
+ "و": 29,
38
+ "ى": 21,
39
+ "ي": 15,
40
+ "–": 17
41
+ }