adid commited on
Commit
7257581
1 Parent(s): b1e8426

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +12 -0
  3. vocab.json +49 -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 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 46,
3
+ "[UNK]": 45,
4
+ "|": 35,
5
+ "ء": 37,
6
+ "آ": 21,
7
+ "أ": 32,
8
+ "ؤ": 28,
9
+ "إ": 42,
10
+ "ئ": 31,
11
+ "ا": 22,
12
+ "ب": 18,
13
+ "ة": 38,
14
+ "ت": 39,
15
+ "ث": 0,
16
+ "ج": 6,
17
+ "ح": 33,
18
+ "خ": 12,
19
+ "د": 15,
20
+ "ذ": 40,
21
+ "ر": 24,
22
+ "ز": 3,
23
+ "س": 4,
24
+ "ش": 10,
25
+ "ص": 8,
26
+ "ض": 9,
27
+ "ط": 26,
28
+ "ظ": 1,
29
+ "ع": 11,
30
+ "غ": 23,
31
+ "ف": 7,
32
+ "ق": 30,
33
+ "ك": 5,
34
+ "ل": 41,
35
+ "م": 43,
36
+ "ن": 27,
37
+ "ه": 29,
38
+ "و": 20,
39
+ "ى": 16,
40
+ "ي": 19,
41
+ "ً": 36,
42
+ "ٌ": 17,
43
+ "ٍ": 13,
44
+ "َ": 34,
45
+ "ُ": 44,
46
+ "ِ": 14,
47
+ "ّ": 2,
48
+ "ْ": 25
49
+ }