sanchit-gandhi HF staff commited on
Commit
79d3850
1 Parent(s): de797d8

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 +47 -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": "mqf",
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 44,
3
+ "'": 42,
4
+ "-": 16,
5
+ "0": 26,
6
+ "1": 28,
7
+ "2": 29,
8
+ "3": 33,
9
+ "4": 27,
10
+ "5": 31,
11
+ "6": 34,
12
+ "7": 36,
13
+ "8": 38,
14
+ "9": 35,
15
+ "a": 3,
16
+ "b": 7,
17
+ "c": 41,
18
+ "d": 39,
19
+ "e": 1,
20
+ "g": 43,
21
+ "h": 37,
22
+ "i": 10,
23
+ "j": 40,
24
+ "k": 9,
25
+ "l": 30,
26
+ "m": 8,
27
+ "n": 4,
28
+ "o": 2,
29
+ "p": 32,
30
+ "r": 6,
31
+ "s": 12,
32
+ "t": 5,
33
+ "u": 13,
34
+ "w": 14,
35
+ "y": 11,
36
+ "|": 0,
37
+ "à": 19,
38
+ "á": 15,
39
+ "è": 23,
40
+ "é": 21,
41
+ "ì": 24,
42
+ "í": 20,
43
+ "ò": 17,
44
+ "ó": 18,
45
+ "ù": 22,
46
+ "ú": 25
47
+ }