sanchit-gandhi commited on
Commit
b635a7f
·
1 Parent(s): 8f7579d

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 +28 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "a",
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": "jav",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "a",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 25,
3
+ "-": 21,
4
+ "a": 0,
5
+ "b": 18,
6
+ "c": 22,
7
+ "d": 14,
8
+ "e": 5,
9
+ "f": 23,
10
+ "g": 3,
11
+ "h": 15,
12
+ "i": 4,
13
+ "j": 20,
14
+ "k": 6,
15
+ "l": 13,
16
+ "m": 12,
17
+ "n": 2,
18
+ "o": 16,
19
+ "p": 11,
20
+ "r": 9,
21
+ "s": 8,
22
+ "t": 10,
23
+ "u": 7,
24
+ "w": 17,
25
+ "y": 19,
26
+ "z": 24,
27
+ "|": 1
28
+ }