sanchit-gandhi HF staff commited on
Commit
c0fed95
1 Parent(s): 663b0c8

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": "j",
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": "mqj",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "j",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 6,
3
+ "'": 26,
4
+ "-": 1,
5
+ "0": 35,
6
+ "1": 14,
7
+ "2": 8,
8
+ "3": 20,
9
+ "4": 19,
10
+ "5": 9,
11
+ "6": 15,
12
+ "7": 18,
13
+ "8": 4,
14
+ "9": 33,
15
+ "_": 28,
16
+ "a": 27,
17
+ "b": 29,
18
+ "c": 34,
19
+ "d": 2,
20
+ "e": 16,
21
+ "f": 22,
22
+ "g": 36,
23
+ "h": 10,
24
+ "i": 25,
25
+ "j": 0,
26
+ "k": 21,
27
+ "l": 7,
28
+ "m": 11,
29
+ "n": 12,
30
+ "o": 32,
31
+ "p": 5,
32
+ "r": 24,
33
+ "s": 13,
34
+ "t": 23,
35
+ "u": 31,
36
+ "w": 30,
37
+ "y": 17,
38
+ "z": 3
39
+ }