plesniar commited on
Commit
e5f5437
1 Parent(s): 7ced2fe

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 40
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "a",
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": "a",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "40": {
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": "tos",
24
+ "model_max_length": 1000000000000000019884624838656,
25
+ "normalize": true,
26
+ "pad_token": "a",
27
+ "phonemize": false,
28
+ "tokenizer_class": "VitsTokenizer",
29
+ "unk_token": "<unk>",
30
+ "verbose": false
31
+ }
vocab.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 39,
3
+ "'": 33,
4
+ "-": 24,
5
+ "0": 35,
6
+ "1": 38,
7
+ "a": 0,
8
+ "b": 28,
9
+ "c": 7,
10
+ "d": 25,
11
+ "e": 23,
12
+ "f": 31,
13
+ "g": 29,
14
+ "h": 8,
15
+ "i": 3,
16
+ "j": 20,
17
+ "k": 12,
18
+ "l": 9,
19
+ "m": 11,
20
+ "n": 5,
21
+ "o": 17,
22
+ "p": 13,
23
+ "q": 18,
24
+ "r": 26,
25
+ "s": 15,
26
+ "t": 6,
27
+ "u": 4,
28
+ "v": 32,
29
+ "x": 10,
30
+ "y": 16,
31
+ "z": 22,
32
+ "|": 2,
33
+ "á": 14,
34
+ "é": 30,
35
+ "ì": 37,
36
+ "í": 19,
37
+ "ï": 36,
38
+ "ñ": 34,
39
+ "ó": 27,
40
+ "ú": 21,
41
+ "̱": 1
42
+ }