sanchit-gandhi commited on
Commit
f28bd77
·
1 Parent(s): 81aba31

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 +41 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "l",
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": "lsi",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "l",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 6,
3
+ "'": 27,
4
+ "-": 3,
5
+ "0": 10,
6
+ "1": 20,
7
+ "2": 24,
8
+ "3": 13,
9
+ "4": 34,
10
+ "5": 17,
11
+ "6": 11,
12
+ "7": 1,
13
+ "_": 23,
14
+ "`": 31,
15
+ "a": 15,
16
+ "b": 32,
17
+ "c": 29,
18
+ "d": 33,
19
+ "e": 9,
20
+ "f": 2,
21
+ "g": 25,
22
+ "h": 8,
23
+ "i": 18,
24
+ "j": 22,
25
+ "k": 12,
26
+ "l": 0,
27
+ "m": 37,
28
+ "n": 16,
29
+ "o": 26,
30
+ "p": 5,
31
+ "q": 4,
32
+ "r": 38,
33
+ "s": 30,
34
+ "t": 36,
35
+ "u": 21,
36
+ "v": 35,
37
+ "w": 19,
38
+ "x": 14,
39
+ "y": 7,
40
+ "z": 28
41
+ }