sanchit-gandhi HF staff commited on
Commit
999a714
1 Parent(s): 2b653f8

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 +48 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "à",
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": "kia",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "à",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 28,
3
+ "'": 24,
4
+ "-": 36,
5
+ "_": 31,
6
+ "a": 37,
7
+ "b": 5,
8
+ "c": 7,
9
+ "d": 2,
10
+ "e": 39,
11
+ "f": 3,
12
+ "g": 15,
13
+ "h": 9,
14
+ "i": 44,
15
+ "j": 40,
16
+ "k": 18,
17
+ "l": 19,
18
+ "m": 4,
19
+ "n": 10,
20
+ "o": 42,
21
+ "p": 12,
22
+ "r": 32,
23
+ "s": 20,
24
+ "t": 45,
25
+ "u": 29,
26
+ "v": 21,
27
+ "w": 38,
28
+ "y": 25,
29
+ "z": 6,
30
+ "à": 0,
31
+ "á": 13,
32
+ "è": 43,
33
+ "é": 26,
34
+ "í": 41,
35
+ "ò": 22,
36
+ "ó": 14,
37
+ "ù": 8,
38
+ "ú": 17,
39
+ "ŋ": 16,
40
+ "ū": 33,
41
+ "ɓ": 1,
42
+ "ɗ": 11,
43
+ "́": 34,
44
+ "̰": 27,
45
+ "ḛ": 23,
46
+ "ḭ": 35,
47
+ "ṵ": 30
48
+ }