sanchit-gandhi HF staff commited on
Commit
e6f5b3c
1 Parent(s): e2568fb

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