nrshoudi commited on
Commit
4b2b61a
1 Parent(s): 66393eb

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 39,
3
+ "<s>": 38
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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "36": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "37": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "38": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "39": {
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_phonemize": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "[PAD]",
42
+ "phone_delimiter_token": " ",
43
+ "phonemizer_backend": "espeak",
44
+ "phonemizer_lang": "en-us",
45
+ "processor_class": "Wav2Vec2Processor",
46
+ "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
47
+ "unk_token": "[UNK]",
48
+ "word_delimiter_token": null
49
+ }
vocab.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 0,
3
+ "[PAD]": 37,
4
+ "[UNK]": 36,
5
+ "آ": 1,
6
+ "أ": 2,
7
+ "إ": 3,
8
+ "ا": 4,
9
+ "اً": 5,
10
+ "ب": 6,
11
+ "ة": 7,
12
+ "ت": 8,
13
+ "ث": 9,
14
+ "ج": 10,
15
+ "ح": 11,
16
+ "خ": 12,
17
+ "د": 13,
18
+ "ذ": 14,
19
+ "ر": 15,
20
+ "ز": 16,
21
+ "س": 17,
22
+ "ش": 18,
23
+ "ص": 19,
24
+ "ض": 20,
25
+ "ط": 21,
26
+ "ظ": 22,
27
+ "ع": 23,
28
+ "غ": 24,
29
+ "ف": 25,
30
+ "ق": 26,
31
+ "ك": 27,
32
+ "ل": 28,
33
+ "لا": 29,
34
+ "م": 30,
35
+ "ن": 31,
36
+ "ه": 32,
37
+ "و": 33,
38
+ "ى": 34,
39
+ "ي": 35
40
+ }