shahukareem commited on
Commit
c81137c
1 Parent(s): f2d6bfc

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 55,
3
+ "<s>": 54
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 53,
3
+ "[UNK]": 52,
4
+ "|": 0,
5
+ "ّ": 1,
6
+ "ހ": 2,
7
+ "ށ": 3,
8
+ "ނ": 4,
9
+ "ރ": 5,
10
+ "ބ": 6,
11
+ "ޅ": 7,
12
+ "ކ": 8,
13
+ "އ": 9,
14
+ "ވ": 10,
15
+ "މ": 11,
16
+ "ފ": 12,
17
+ "ދ": 13,
18
+ "ތ": 14,
19
+ "ލ": 15,
20
+ "ގ": 16,
21
+ "ޏ": 17,
22
+ "ސ": 18,
23
+ "ޑ": 19,
24
+ "ޒ": 20,
25
+ "ޓ": 21,
26
+ "ޔ": 22,
27
+ "ޕ": 23,
28
+ "ޖ": 24,
29
+ "ޗ": 25,
30
+ "ޘ": 26,
31
+ "ޙ": 27,
32
+ "ޚ": 28,
33
+ "ޛ": 29,
34
+ "ޝ": 30,
35
+ "ޞ": 31,
36
+ "ޟ": 32,
37
+ "ޠ": 33,
38
+ "ޡ": 34,
39
+ "ޢ": 35,
40
+ "ޣ": 36,
41
+ "ޤ": 37,
42
+ "ޥ": 38,
43
+ "ަ": 39,
44
+ "ާ": 40,
45
+ "ި": 41,
46
+ "ީ": 42,
47
+ "ު": 43,
48
+ "ޫ": 44,
49
+ "ެ": 45,
50
+ "ޭ": 46,
51
+ "ޮ": 47,
52
+ "ޯ": 48,
53
+ "ް": 49,
54
+ "ﷲ": 50,
55
+ "ﷺ": 51
56
+ }