sanchit-gandhi HF staff commited on
Commit
7ea64b1
1 Parent(s): 01484dc

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": "í",
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": "pui",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "í",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 33,
3
+ "-": 29,
4
+ "0": 1,
5
+ "2": 13,
6
+ "4": 30,
7
+ "7": 32,
8
+ "9": 39,
9
+ "_": 5,
10
+ "a": 11,
11
+ "b": 18,
12
+ "c": 37,
13
+ "d": 7,
14
+ "e": 31,
15
+ "f": 36,
16
+ "g": 38,
17
+ "h": 14,
18
+ "i": 34,
19
+ "j": 15,
20
+ "k": 12,
21
+ "l": 17,
22
+ "m": 4,
23
+ "n": 6,
24
+ "o": 26,
25
+ "p": 10,
26
+ "q": 28,
27
+ "r": 41,
28
+ "s": 40,
29
+ "t": 20,
30
+ "u": 35,
31
+ "v": 21,
32
+ "w": 27,
33
+ "x": 8,
34
+ "y": 16,
35
+ "z": 25,
36
+ "á": 3,
37
+ "é": 23,
38
+ "í": 0,
39
+ "ñ": 22,
40
+ "ó": 9,
41
+ "ú": 19,
42
+ "ü": 2,
43
+ "ŕ": 24
44
+ }