sanchit-gandhi HF staff commited on
Commit
4ac527f
1 Parent(s): daf9cf4

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 +50 -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": "gym",
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 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 47,
3
+ "-": 43,
4
+ "0": 36,
5
+ "1": 34,
6
+ "2": 35,
7
+ "3": 42,
8
+ "4": 40,
9
+ "5": 41,
10
+ "6": 38,
11
+ "7": 46,
12
+ "8": 39,
13
+ "9": 44,
14
+ "a": 2,
15
+ "b": 9,
16
+ "c": 24,
17
+ "d": 16,
18
+ "e": 1,
19
+ "f": 28,
20
+ "g": 15,
21
+ "h": 26,
22
+ "i": 5,
23
+ "j": 17,
24
+ "k": 4,
25
+ "l": 22,
26
+ "m": 10,
27
+ "n": 3,
28
+ "o": 13,
29
+ "p": 23,
30
+ "q": 33,
31
+ "r": 6,
32
+ "s": 19,
33
+ "t": 7,
34
+ "u": 12,
35
+ "v": 30,
36
+ "w": 11,
37
+ "x": 45,
38
+ "y": 18,
39
+ "z": 32,
40
+ "|": 0,
41
+ "á": 31,
42
+ "ä": 8,
43
+ "é": 25,
44
+ "í": 27,
45
+ "ñ": 21,
46
+ "ó": 29,
47
+ "ö": 14,
48
+ "ú": 37,
49
+ "ü": 20
50
+ }