sanchit-gandhi HF staff commited on
Commit
36a6696
1 Parent(s): 7cf630f

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 +49 -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": "zpo",
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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 1,
3
+ "'": 26,
4
+ "-": 0,
5
+ "0": 45,
6
+ "1": 43,
7
+ "2": 15,
8
+ "3": 3,
9
+ "4": 40,
10
+ "5": 44,
11
+ "6": 23,
12
+ "7": 10,
13
+ "8": 13,
14
+ "9": 17,
15
+ "_": 2,
16
+ "a": 8,
17
+ "b": 32,
18
+ "c": 4,
19
+ "d": 46,
20
+ "e": 24,
21
+ "f": 30,
22
+ "g": 37,
23
+ "h": 31,
24
+ "i": 7,
25
+ "j": 28,
26
+ "k": 19,
27
+ "l": 25,
28
+ "m": 14,
29
+ "n": 6,
30
+ "o": 38,
31
+ "p": 36,
32
+ "q": 11,
33
+ "r": 22,
34
+ "s": 33,
35
+ "t": 5,
36
+ "u": 21,
37
+ "v": 18,
38
+ "w": 41,
39
+ "x": 27,
40
+ "y": 20,
41
+ "z": 42,
42
+ "á": 16,
43
+ "é": 12,
44
+ "í": 34,
45
+ "ñ": 29,
46
+ "ó": 35,
47
+ "ú": 9,
48
+ "—": 39
49
+ }