sanchit-gandhi HF staff commited on
Commit
02692bb
1 Parent(s): 793bb55

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