sanchit-gandhi HF staff commited on
Commit
03d61c9
1 Parent(s): 6d569c9

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 +36 -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": "mhu",
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 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 30,
3
+ "'": 3,
4
+ "-": 1,
5
+ "_": 13,
6
+ "a": 9,
7
+ "b": 32,
8
+ "c": 17,
9
+ "d": 10,
10
+ "e": 23,
11
+ "g": 20,
12
+ "h": 7,
13
+ "i": 33,
14
+ "j": 27,
15
+ "k": 4,
16
+ "l": 18,
17
+ "m": 29,
18
+ "n": 16,
19
+ "o": 19,
20
+ "p": 5,
21
+ "q": 2,
22
+ "r": 12,
23
+ "s": 11,
24
+ "t": 25,
25
+ "u": 6,
26
+ "v": 15,
27
+ "w": 31,
28
+ "y": 28,
29
+ "z": 22,
30
+ "ã": 26,
31
+ "ü": 14,
32
+ "ũ": 8,
33
+ "ǃ": 24,
34
+ "̃": 0,
35
+ "ẽ": 21
36
+ }