navaaesarosh commited on
Commit
f322eee
1 Parent(s): 76db78e

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 95,
3
+ "<s>": 94
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 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": 1,
3
+ "1": 2,
4
+ "2": 3,
5
+ "3": 4,
6
+ "4": 5,
7
+ "5": 6,
8
+ "6": 7,
9
+ "7": 8,
10
+ "8": 9,
11
+ "9": 10,
12
+ "[PAD]": 93,
13
+ "[UNK]": 92,
14
+ "`": 11,
15
+ "a": 12,
16
+ "b": 13,
17
+ "c": 14,
18
+ "d": 15,
19
+ "e": 16,
20
+ "f": 17,
21
+ "i": 18,
22
+ "l": 19,
23
+ "m": 20,
24
+ "n": 21,
25
+ "o": 22,
26
+ "p": 23,
27
+ "r": 24,
28
+ "s": 25,
29
+ "t": 26,
30
+ "u": 27,
31
+ "v": 28,
32
+ "w": 29,
33
+ "|": 0,
34
+ "ء": 30,
35
+ "آ": 31,
36
+ "أ": 32,
37
+ "ؤ": 33,
38
+ "ئ": 34,
39
+ "ا": 35,
40
+ "ب": 36,
41
+ "ت": 37,
42
+ "ث": 38,
43
+ "ج": 39,
44
+ "ح": 40,
45
+ "خ": 41,
46
+ "د": 42,
47
+ "ذ": 43,
48
+ "ر": 44,
49
+ "ز": 45,
50
+ "س": 46,
51
+ "ش": 47,
52
+ "ص": 48,
53
+ "ض": 49,
54
+ "ط": 50,
55
+ "ظ": 51,
56
+ "ع": 52,
57
+ "غ": 53,
58
+ "ف": 54,
59
+ "ق": 55,
60
+ "ك": 56,
61
+ "ل": 57,
62
+ "م": 58,
63
+ "ن": 59,
64
+ "ه": 60,
65
+ "و": 61,
66
+ "ى": 62,
67
+ "ي": 63,
68
+ "ٹ": 64,
69
+ "پ": 65,
70
+ "چ": 66,
71
+ "ڈ": 67,
72
+ "ڑ": 68,
73
+ "ژ": 69,
74
+ "ک": 70,
75
+ "گ": 71,
76
+ "ں": 72,
77
+ "ھ": 73,
78
+ "ہ": 74,
79
+ "ۂ": 75,
80
+ "ۃ": 76,
81
+ "ی": 77,
82
+ "ے": 78,
83
+ "ۓ": 79,
84
+ "ﭨ": 80,
85
+ "ﮭ": 81,
86
+ "ﮯ": 82,
87
+ "ﯾ": 83,
88
+ "ﷲ": 84,
89
+ "ﷺ": 85,
90
+ "ﺗ": 86,
91
+ "ﺘ": 87,
92
+ "ﺩ": 88,
93
+ "ﺲ": 89,
94
+ "ﻧ": 90,
95
+ "ﻮ": 91
96
+ }