sanchit-gandhi HF staff commited on
Commit
c979dbc
1 Parent(s): d5b3edd

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": "ñ",
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": "mxb",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ñ",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 19,
3
+ "'": 14,
4
+ "-": 16,
5
+ "0": 10,
6
+ "1": 22,
7
+ "2": 1,
8
+ "3": 28,
9
+ "4": 18,
10
+ "5": 12,
11
+ "6": 25,
12
+ "7": 38,
13
+ "8": 8,
14
+ "9": 32,
15
+ "_": 15,
16
+ "a": 40,
17
+ "b": 30,
18
+ "c": 37,
19
+ "d": 21,
20
+ "e": 3,
21
+ "f": 41,
22
+ "g": 36,
23
+ "h": 11,
24
+ "i": 24,
25
+ "j": 34,
26
+ "k": 4,
27
+ "l": 31,
28
+ "m": 43,
29
+ "n": 46,
30
+ "o": 35,
31
+ "p": 26,
32
+ "q": 23,
33
+ "r": 2,
34
+ "s": 13,
35
+ "t": 17,
36
+ "u": 39,
37
+ "v": 33,
38
+ "x": 42,
39
+ "y": 7,
40
+ "z": 27,
41
+ "á": 20,
42
+ "é": 9,
43
+ "í": 29,
44
+ "ñ": 0,
45
+ "ó": 45,
46
+ "ú": 6,
47
+ "ü": 44,
48
+ "̱": 5
49
+ }