sanchit-gandhi HF staff commited on
Commit
02eb69b
1 Parent(s): d119782

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 +42 -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": "ade",
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 39,
3
+ "'": 37,
4
+ "-": 25,
5
+ "a": 1,
6
+ "b": 5,
7
+ "c": 38,
8
+ "d": 18,
9
+ "e": 4,
10
+ "f": 20,
11
+ "g": 6,
12
+ "h": 36,
13
+ "i": 8,
14
+ "k": 13,
15
+ "l": 16,
16
+ "m": 19,
17
+ "n": 3,
18
+ "o": 14,
19
+ "p": 23,
20
+ "r": 15,
21
+ "s": 21,
22
+ "t": 9,
23
+ "u": 17,
24
+ "w": 10,
25
+ "y": 12,
26
+ "|": 0,
27
+ "à": 24,
28
+ "â": 2,
29
+ "ã": 27,
30
+ "å": 31,
31
+ "æ": 7,
32
+ "è": 26,
33
+ "ì": 32,
34
+ "î": 30,
35
+ "ò": 35,
36
+ "ô": 11,
37
+ "õ": 28,
38
+ "ù": 29,
39
+ "û": 22,
40
+ "ü": 33,
41
+ "ǹ": 34
42
+ }