sanchit-gandhi HF staff commited on
Commit
7291afd
1 Parent(s): ce3f7ea

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 +45 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "à",
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": "por",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "à",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 32,
3
+ "'": 11,
4
+ "-": 19,
5
+ "1": 2,
6
+ "2": 5,
7
+ "4": 16,
8
+ "_": 13,
9
+ "a": 38,
10
+ "b": 31,
11
+ "c": 22,
12
+ "d": 40,
13
+ "e": 27,
14
+ "f": 30,
15
+ "g": 20,
16
+ "h": 6,
17
+ "i": 29,
18
+ "j": 39,
19
+ "l": 4,
20
+ "m": 18,
21
+ "n": 35,
22
+ "o": 28,
23
+ "p": 8,
24
+ "q": 21,
25
+ "r": 33,
26
+ "s": 14,
27
+ "t": 26,
28
+ "u": 3,
29
+ "v": 17,
30
+ "x": 10,
31
+ "z": 23,
32
+ "à": 0,
33
+ "á": 42,
34
+ "â": 24,
35
+ "ã": 9,
36
+ "ç": 15,
37
+ "é": 7,
38
+ "ê": 12,
39
+ "í": 25,
40
+ "ó": 37,
41
+ "ô": 34,
42
+ "õ": 41,
43
+ "ú": 1,
44
+ "—": 36
45
+ }