sanchit-gandhi HF staff commited on
Commit
6c604c8
1 Parent(s): 97f4b27

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