sanchit-gandhi HF staff commited on
Commit
0222559
1 Parent(s): a5faba8

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 +44 -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": "sgb",
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 41,
3
+ "-": 21,
4
+ "0": 31,
5
+ "1": 33,
6
+ "2": 34,
7
+ "3": 40,
8
+ "4": 39,
9
+ "5": 37,
10
+ "6": 38,
11
+ "a": 0,
12
+ "b": 14,
13
+ "c": 23,
14
+ "d": 19,
15
+ "e": 20,
16
+ "f": 26,
17
+ "g": 12,
18
+ "h": 6,
19
+ "i": 3,
20
+ "j": 22,
21
+ "k": 9,
22
+ "l": 8,
23
+ "m": 7,
24
+ "n": 2,
25
+ "o": 5,
26
+ "p": 11,
27
+ "q": 29,
28
+ "r": 16,
29
+ "s": 17,
30
+ "t": 10,
31
+ "u": 15,
32
+ "v": 28,
33
+ "w": 18,
34
+ "x": 32,
35
+ "y": 4,
36
+ "z": 27,
37
+ "|": 1,
38
+ "á": 24,
39
+ "ê": 13,
40
+ "í": 25,
41
+ "ñ": 36,
42
+ "ó": 35,
43
+ "ú": 30
44
+ }