yassine benlaria commited on
Commit
c61fd65
1 Parent(s): 0f483e8

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +13 -0
  3. vocab.json +45 -0
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "target_lang": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "unk_token": "[UNK]",
12
+ "word_delimiter_token": "|"
13
+ }
vocab.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 42,
3
+ "[UNK]": 41,
4
+ "p": 24,
5
+ "|": 19,
6
+ "ء": 37,
7
+ "آ": 1,
8
+ "أ": 30,
9
+ "ؤ": 29,
10
+ "إ": 5,
11
+ "ئ": 12,
12
+ "ا": 35,
13
+ "ب": 22,
14
+ "ة": 39,
15
+ "ت": 14,
16
+ "ث": 34,
17
+ "ج": 4,
18
+ "ح": 23,
19
+ "خ": 20,
20
+ "د": 36,
21
+ "ذ": 17,
22
+ "ر": 38,
23
+ "ز": 25,
24
+ "س": 9,
25
+ "ش": 0,
26
+ "ص": 6,
27
+ "ض": 33,
28
+ "ط": 27,
29
+ "ظ": 16,
30
+ "ع": 18,
31
+ "غ": 8,
32
+ "ف": 3,
33
+ "ق": 7,
34
+ "ك": 40,
35
+ "ل": 32,
36
+ "م": 26,
37
+ "ن": 15,
38
+ "ه": 2,
39
+ "و": 11,
40
+ "ى": 28,
41
+ "ي": 21,
42
+ "ٱ": 31,
43
+ "ڤ": 13,
44
+ "ی": 10
45
+ }