sanchit-gandhi HF staff commited on
Commit
c825a72
1 Parent(s): 13c32dc

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +4 -0
  2. tokenizer_config.json +12 -0
  3. vocab.json +44 -0
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 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "clean_up_tokenization_spaces": true,
4
+ "is_uroman": false,
5
+ "language": "cto",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "a",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 41,
3
+ "'": 5,
4
+ "-": 39,
5
+ "a": 0,
6
+ "b": 3,
7
+ "c": 28,
8
+ "d": 10,
9
+ "e": 4,
10
+ "f": 35,
11
+ "g": 27,
12
+ "h": 22,
13
+ "i": 6,
14
+ "j": 20,
15
+ "k": 16,
16
+ "l": 31,
17
+ "m": 9,
18
+ "n": 17,
19
+ "o": 18,
20
+ "p": 25,
21
+ "q": 40,
22
+ "r": 2,
23
+ "s": 15,
24
+ "t": 14,
25
+ "u": 11,
26
+ "v": 38,
27
+ "w": 12,
28
+ "y": 26,
29
+ "z": 13,
30
+ "|": 1,
31
+ "á": 37,
32
+ "ã": 7,
33
+ "é": 34,
34
+ "í": 33,
35
+ "ñ": 32,
36
+ "ó": 36,
37
+ "õ": 30,
38
+ "ú": 29,
39
+ "ĩ": 23,
40
+ "ũ": 19,
41
+ "ʉ": 8,
42
+ "̃": 24,
43
+ "ẽ": 21
44
+ }