sanchit-gandhi HF staff commited on
Commit
41c5973
1 Parent(s): 2c5fbc7

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