hadiqa123 commited on
Commit
d6d207f
1 Parent(s): 4b6df17

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 47,
3
+ "<s>": 46
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "[PAD]",
21
+ "unk_token": "[UNK]"
22
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "./",
6
+ "pad_token": "[PAD]",
7
+ "replace_word_delimiter_char": " ",
8
+ "special_tokens_map_file": null,
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 45,
3
+ "[UNK]": 44,
4
+ "|": 0,
5
+ "ء": 1,
6
+ "ا": 2,
7
+ "ب": 3,
8
+ "ت": 4,
9
+ "ث": 5,
10
+ "ج": 6,
11
+ "ح": 7,
12
+ "خ": 8,
13
+ "د": 9,
14
+ "ذ": 10,
15
+ "ر": 11,
16
+ "ز": 12,
17
+ "س": 13,
18
+ "ش": 14,
19
+ "ص": 15,
20
+ "ض": 16,
21
+ "ط": 17,
22
+ "ظ": 18,
23
+ "ع": 19,
24
+ "غ": 20,
25
+ "ف": 21,
26
+ "ق": 22,
27
+ "ل": 23,
28
+ "م": 24,
29
+ "ن": 25,
30
+ "و": 26,
31
+ "ى": 27,
32
+ "ي": 28,
33
+ "ً": 29,
34
+ "ٓ": 30,
35
+ "ٹ": 31,
36
+ "پ": 32,
37
+ "چ": 33,
38
+ "ڈ": 34,
39
+ "ڑ": 35,
40
+ "ژ": 36,
41
+ "ک": 37,
42
+ "گ": 38,
43
+ "ں": 39,
44
+ "ھ": 40,
45
+ "ہ": 41,
46
+ "ی": 42,
47
+ "ے": 43
48
+ }