sanchit-gandhi HF staff commited on
Commit
3d1d988
1 Parent(s): be4d2e3

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": "|",
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": "ace",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "|",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 41,
3
+ "'": 31,
4
+ "-": 24,
5
+ "0": 35,
6
+ "1": 39,
7
+ "2": 40,
8
+ "3": 38,
9
+ "4": 37,
10
+ "6": 36,
11
+ "`": 34,
12
+ "a": 1,
13
+ "b": 11,
14
+ "c": 25,
15
+ "d": 19,
16
+ "e": 3,
17
+ "f": 29,
18
+ "g": 5,
19
+ "h": 7,
20
+ "i": 8,
21
+ "j": 18,
22
+ "k": 9,
23
+ "l": 14,
24
+ "m": 10,
25
+ "n": 2,
26
+ "o": 12,
27
+ "p": 17,
28
+ "q": 32,
29
+ "r": 15,
30
+ "s": 16,
31
+ "t": 6,
32
+ "u": 4,
33
+ "w": 21,
34
+ "y": 13,
35
+ "z": 30,
36
+ "|": 0,
37
+ "á": 27,
38
+ "é": 20,
39
+ "ë": 23,
40
+ "ó": 28,
41
+ "ô": 22,
42
+ "ö": 26,
43
+ "ú": 33
44
+ }