sanchit-gandhi HF staff commited on
Commit
7ccaf73
1 Parent(s): 0e42f78

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