sanchit-gandhi commited on
Commit
696ada6
1 Parent(s): 91370af

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 +50 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "贸",
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": "lns",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "贸",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 27,
3
+ "-": 20,
4
+ "_": 36,
5
+ "a": 18,
6
+ "b": 6,
7
+ "c": 16,
8
+ "d": 28,
9
+ "e": 9,
10
+ "f": 46,
11
+ "g": 39,
12
+ "h": 32,
13
+ "i": 31,
14
+ "j": 42,
15
+ "k": 5,
16
+ "l": 11,
17
+ "m": 25,
18
+ "n": 15,
19
+ "o": 19,
20
+ "p": 47,
21
+ "r": 30,
22
+ "s": 8,
23
+ "t": 35,
24
+ "u": 1,
25
+ "v": 34,
26
+ "w": 43,
27
+ "y": 2,
28
+ "z": 24,
29
+ "脿": 40,
30
+ "谩": 33,
31
+ "猫": 38,
32
+ "茅": 29,
33
+ "矛": 23,
34
+ "铆": 37,
35
+ "貌": 22,
36
+ "贸": 0,
37
+ "霉": 13,
38
+ "煤": 14,
39
+ "臎": 44,
40
+ "艐": 10,
41
+ "菐": 21,
42
+ "菒": 41,
43
+ "菕": 4,
44
+ "菙": 7,
45
+ "蓹": 3,
46
+ "始": 17,
47
+ "虁": 12,
48
+ "虂": 45,
49
+ "虒": 26
50
+ }