sanchit-gandhi HF staff commited on
Commit
6ae2f20
1 Parent(s): b0504da

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