sanchit-gandhi HF staff commited on
Commit
d2a7a9f
1 Parent(s): 750fa20

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 +47 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "7",
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": "spa",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "7",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 27,
3
+ "0": 5,
4
+ "1": 24,
5
+ "2": 36,
6
+ "3": 32,
7
+ "4": 12,
8
+ "5": 6,
9
+ "6": 44,
10
+ "7": 0,
11
+ "8": 8,
12
+ "9": 23,
13
+ "_": 22,
14
+ "a": 1,
15
+ "b": 31,
16
+ "c": 3,
17
+ "d": 29,
18
+ "e": 39,
19
+ "f": 25,
20
+ "g": 34,
21
+ "h": 19,
22
+ "i": 37,
23
+ "j": 33,
24
+ "k": 15,
25
+ "l": 35,
26
+ "m": 13,
27
+ "n": 20,
28
+ "o": 41,
29
+ "p": 9,
30
+ "q": 18,
31
+ "r": 43,
32
+ "s": 16,
33
+ "t": 26,
34
+ "u": 38,
35
+ "v": 2,
36
+ "x": 28,
37
+ "y": 10,
38
+ "z": 11,
39
+ "á": 17,
40
+ "é": 21,
41
+ "í": 30,
42
+ "ñ": 42,
43
+ "ó": 7,
44
+ "ú": 40,
45
+ "ü": 14,
46
+ "—": 4
47
+ }