sanchit-gandhi commited on
Commit
5552f96
·
1 Parent(s): c67cd1b

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 +39 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "i",
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": "mxt",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "i",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 23,
3
+ "_": 33,
4
+ "a": 22,
5
+ "b": 19,
6
+ "c": 10,
7
+ "d": 32,
8
+ "e": 29,
9
+ "f": 9,
10
+ "g": 34,
11
+ "h": 3,
12
+ "i": 0,
13
+ "j": 7,
14
+ "k": 6,
15
+ "l": 17,
16
+ "m": 27,
17
+ "n": 20,
18
+ "o": 26,
19
+ "p": 21,
20
+ "q": 1,
21
+ "r": 5,
22
+ "s": 11,
23
+ "t": 30,
24
+ "u": 24,
25
+ "v": 18,
26
+ "x": 13,
27
+ "y": 36,
28
+ "z": 15,
29
+ "á": 35,
30
+ "é": 8,
31
+ "í": 12,
32
+ "ñ": 25,
33
+ "ó": 2,
34
+ "ú": 31,
35
+ "ɨ": 16,
36
+ "́": 28,
37
+ "̱": 4,
38
+ "ṉ": 14
39
+ }