charbossly commited on
Commit
e4faf28
1 Parent(s): c7e3a50

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 43
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "|",
3
+ "unk_token": "<unk>"
4
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "|",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "43": {
13
+ "content": "<unk>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "clean_up_tokenization_spaces": true,
22
+ "is_uroman": false,
23
+ "language": "yor",
24
+ "model_max_length": 1000000000000000019884624838656,
25
+ "normalize": true,
26
+ "pad_token": "|",
27
+ "phonemize": false,
28
+ "tokenizer_class": "VitsTokenizer",
29
+ "unk_token": "<unk>",
30
+ "verbose": false
31
+ }
vocab.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 42,
3
+ "'": 41,
4
+ "-": 38,
5
+ "a": 8,
6
+ "b": 10,
7
+ "d": 33,
8
+ "e": 27,
9
+ "f": 30,
10
+ "g": 21,
11
+ "h": 37,
12
+ "i": 4,
13
+ "j": 28,
14
+ "k": 16,
15
+ "l": 14,
16
+ "m": 22,
17
+ "n": 1,
18
+ "o": 20,
19
+ "p": 25,
20
+ "r": 9,
21
+ "s": 18,
22
+ "t": 7,
23
+ "u": 26,
24
+ "w": 12,
25
+ "y": 23,
26
+ "|": 0,
27
+ "à": 5,
28
+ "á": 17,
29
+ "è": 34,
30
+ "é": 32,
31
+ "ì": 11,
32
+ "í": 2,
33
+ "ò": 29,
34
+ "ó": 24,
35
+ "ù": 35,
36
+ "ú": 19,
37
+ "ń": 36,
38
+ "ǹ": 39,
39
+ "̀": 15,
40
+ "́": 13,
41
+ "ṣ": 31,
42
+ "ẹ": 6,
43
+ "ọ": 3,
44
+ "—": 40
45
+ }