sanchit-gandhi HF staff commited on
Commit
5aaf91f
1 Parent(s): 7710971

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