marziye-A commited on
Commit
d2c5f73
1 Parent(s): b4bf149

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 38,
3
+ "<s>": 37
4
+ }
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "35": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "36": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "37": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "38": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "replace_word_delimiter_char": " ",
43
+ "target_lang": null,
44
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
45
+ "unk_token": "[UNK]",
46
+ "word_delimiter_token": "|"
47
+ }
vocab.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 36,
3
+ "[UNK]": 35,
4
+ "|": 0,
5
+ "آ": 1,
6
+ "ئ": 2,
7
+ "ا": 3,
8
+ "ب": 4,
9
+ "ت": 5,
10
+ "ث": 6,
11
+ "ج": 7,
12
+ "ح": 8,
13
+ "خ": 9,
14
+ "د": 10,
15
+ "ذ": 11,
16
+ "ر": 12,
17
+ "ز": 13,
18
+ "س": 14,
19
+ "ش": 15,
20
+ "ص": 16,
21
+ "ض": 17,
22
+ "ط": 18,
23
+ "ظ": 19,
24
+ "ع": 20,
25
+ "غ": 21,
26
+ "ف": 22,
27
+ "ق": 23,
28
+ "ل": 24,
29
+ "م": 25,
30
+ "ن": 26,
31
+ "ه": 27,
32
+ "و": 28,
33
+ "پ": 29,
34
+ "چ": 30,
35
+ "ژ": 31,
36
+ "ک": 32,
37
+ "گ": 33,
38
+ "ی": 34
39
+ }