sanchit-gandhi commited on
Commit
b83a284
·
1 Parent(s): 27de262

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": "̃",
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": "myy",
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 9,
3
+ "'": 34,
4
+ "_": 26,
5
+ "a": 10,
6
+ "b": 2,
7
+ "c": 41,
8
+ "d": 39,
9
+ "e": 16,
10
+ "f": 14,
11
+ "g": 1,
12
+ "h": 38,
13
+ "i": 42,
14
+ "j": 36,
15
+ "k": 28,
16
+ "l": 22,
17
+ "m": 19,
18
+ "n": 20,
19
+ "o": 40,
20
+ "p": 11,
21
+ "q": 32,
22
+ "r": 15,
23
+ "s": 33,
24
+ "t": 31,
25
+ "u": 13,
26
+ "v": 29,
27
+ "w": 12,
28
+ "x": 18,
29
+ "y": 25,
30
+ "z": 5,
31
+ "á": 44,
32
+ "ã": 37,
33
+ "é": 7,
34
+ "í": 45,
35
+ "ñ": 4,
36
+ "ó": 30,
37
+ "õ": 3,
38
+ "ú": 24,
39
+ "ü": 35,
40
+ "ĩ": 43,
41
+ "ũ": 17,
42
+ "ʉ": 8,
43
+ "́": 23,
44
+ "̃": 0,
45
+ "ẽ": 27,
46
+ "‍": 6,
47
+ "—": 21
48
+ }