diallomama commited on
Commit
7f3d23c
1 Parent(s): ae32b15

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 69,
3
+ "<s>": 68
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
+ "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 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 67,
3
+ "[UNK]": 66,
4
+ "_": 1,
5
+ "e": 2,
6
+ "g": 3,
7
+ "t": 4,
8
+ "|": 0,
9
+ "،": 5,
10
+ "؛": 6,
11
+ "؟": 7,
12
+ "ء": 8,
13
+ "آ": 9,
14
+ "أ": 10,
15
+ "ؤ": 11,
16
+ "إ": 12,
17
+ "ئ": 13,
18
+ "ا": 14,
19
+ "ب": 15,
20
+ "ة": 16,
21
+ "ت": 17,
22
+ "ث": 18,
23
+ "ج": 19,
24
+ "ح": 20,
25
+ "خ": 21,
26
+ "د": 22,
27
+ "ذ": 23,
28
+ "ر": 24,
29
+ "ز": 25,
30
+ "س": 26,
31
+ "ش": 27,
32
+ "ص": 28,
33
+ "ض": 29,
34
+ "ط": 30,
35
+ "ظ": 31,
36
+ "ع": 32,
37
+ "غ": 33,
38
+ "ـ": 34,
39
+ "ف": 35,
40
+ "ق": 36,
41
+ "ك": 37,
42
+ "ل": 38,
43
+ "م": 39,
44
+ "ن": 40,
45
+ "ه": 41,
46
+ "و": 42,
47
+ "ى": 43,
48
+ "ي": 44,
49
+ "ً": 45,
50
+ "ٌ": 46,
51
+ "ٍ": 47,
52
+ "َ": 48,
53
+ "ُ": 49,
54
+ "ِ": 50,
55
+ "ّ": 51,
56
+ "ْ": 52,
57
+ "ٰ": 53,
58
+ "چ": 54,
59
+ "ڨ": 55,
60
+ "ک": 56,
61
+ "ھ": 57,
62
+ "ی": 58,
63
+ "ۖ": 59,
64
+ "ۚ": 60,
65
+ "—": 61,
66
+ "”": 62,
67
+ "☭": 63,
68
+ "ﺃ": 64,
69
+ "ﻻ": 65
70
+ }