sanchit-gandhi HF staff commited on
Commit
ba9001d
1 Parent(s): a71c354

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 +61 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "6",
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": "luc",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "6",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 19,
3
+ "'": 6,
4
+ "-": 16,
5
+ "0": 44,
6
+ "1": 53,
7
+ "2": 20,
8
+ "3": 11,
9
+ "4": 21,
10
+ "6": 0,
11
+ "_": 15,
12
+ "a": 4,
13
+ "b": 56,
14
+ "c": 49,
15
+ "d": 50,
16
+ "e": 2,
17
+ "f": 41,
18
+ "g": 55,
19
+ "h": 29,
20
+ "i": 13,
21
+ "j": 45,
22
+ "k": 47,
23
+ "l": 32,
24
+ "m": 43,
25
+ "n": 1,
26
+ "o": 27,
27
+ "p": 9,
28
+ "r": 57,
29
+ "s": 7,
30
+ "t": 40,
31
+ "u": 34,
32
+ "v": 28,
33
+ "w": 36,
34
+ "y": 39,
35
+ "z": 48,
36
+ "á": 22,
37
+ "â": 12,
38
+ "ã": 3,
39
+ "é": 51,
40
+ "ê": 8,
41
+ "í": 17,
42
+ "î": 10,
43
+ "ó": 23,
44
+ "ô": 5,
45
+ "õ": 31,
46
+ "ú": 46,
47
+ "û": 42,
48
+ "ĩ": 25,
49
+ "ŋ": 24,
50
+ "ũ": 52,
51
+ "́": 18,
52
+ "̂": 54,
53
+ "̃": 58,
54
+ "ẹ": 37,
55
+ "ẽ": 35,
56
+ "ệ": 38,
57
+ "ị": 33,
58
+ "ọ": 30,
59
+ "ộ": 14,
60
+ "ụ": 26
61
+ }