sanchit-gandhi HF staff commited on
Commit
a6b7447
1 Parent(s): ee385f6

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 +43 -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": "maa-dialect_sanjerónimo",
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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 40,
3
+ "'": 10,
4
+ "-": 39,
5
+ "a": 1,
6
+ "b": 31,
7
+ "c": 23,
8
+ "d": 24,
9
+ "e": 12,
10
+ "f": 34,
11
+ "g": 14,
12
+ "h": 22,
13
+ "i": 4,
14
+ "j": 5,
15
+ "k": 6,
16
+ "l": 19,
17
+ "m": 21,
18
+ "n": 2,
19
+ "o": 8,
20
+ "p": 35,
21
+ "q": 38,
22
+ "r": 29,
23
+ "s": 9,
24
+ "t": 7,
25
+ "u": 32,
26
+ "v": 37,
27
+ "x": 13,
28
+ "y": 26,
29
+ "z": 36,
30
+ "|": 0,
31
+ "à": 18,
32
+ "á": 17,
33
+ "è": 25,
34
+ "é": 27,
35
+ "ì": 16,
36
+ "í": 15,
37
+ "ñ": 28,
38
+ "ò": 20,
39
+ "ó": 30,
40
+ "ú": 33,
41
+ "̱": 3,
42
+ "‐": 11
43
+ }