sanchit-gandhi HF staff commited on
Commit
02cafec
1 Parent(s): daa3f13

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 +39 -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": "tuf",
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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 4,
3
+ "-": 30,
4
+ "_": 6,
5
+ "a": 10,
6
+ "b": 7,
7
+ "c": 18,
8
+ "d": 28,
9
+ "e": 19,
10
+ "f": 14,
11
+ "g": 34,
12
+ "h": 20,
13
+ "i": 16,
14
+ "j": 1,
15
+ "k": 23,
16
+ "l": 24,
17
+ "m": 13,
18
+ "n": 22,
19
+ "o": 12,
20
+ "p": 29,
21
+ "q": 35,
22
+ "r": 17,
23
+ "s": 26,
24
+ "t": 21,
25
+ "u": 2,
26
+ "v": 27,
27
+ "w": 15,
28
+ "x": 11,
29
+ "y": 5,
30
+ "z": 3,
31
+ "á": 31,
32
+ "é": 36,
33
+ "í": 32,
34
+ "ñ": 8,
35
+ "ó": 25,
36
+ "ú": 33,
37
+ "̃": 0,
38
+ "—": 9
39
+ }