sanchit-gandhi HF staff commited on
Commit
5ef43fd
1 Parent(s): b0b5827

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