sanchit-gandhi HF staff commited on
Commit
be76617
1 Parent(s): 153e508

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 +49 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "o",
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": "mbj",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "o",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 17,
3
+ "'": 46,
4
+ "-": 25,
5
+ "0": 5,
6
+ "1": 41,
7
+ "2": 35,
8
+ "3": 23,
9
+ "4": 22,
10
+ "5": 30,
11
+ "6": 32,
12
+ "7": 40,
13
+ "8": 39,
14
+ "9": 6,
15
+ "_": 38,
16
+ "a": 33,
17
+ "b": 8,
18
+ "d": 3,
19
+ "e": 16,
20
+ "g": 12,
21
+ "h": 15,
22
+ "i": 19,
23
+ "j": 26,
24
+ "k": 9,
25
+ "l": 29,
26
+ "m": 31,
27
+ "n": 36,
28
+ "o": 0,
29
+ "p": 4,
30
+ "r": 37,
31
+ "s": 2,
32
+ "t": 1,
33
+ "u": 14,
34
+ "w": 18,
35
+ "y": 7,
36
+ "ã": 27,
37
+ "ä": 21,
38
+ "é": 20,
39
+ "ë": 28,
40
+ "ó": 13,
41
+ "õ": 43,
42
+ "ĩ": 45,
43
+ "ũ": 11,
44
+ "ǟ": 42,
45
+ "̃": 10,
46
+ "ẽ": 34,
47
+ "ỹ": 44,
48
+ "—": 24
49
+ }