sanchit-gandhi commited on
Commit
ea89dcd
·
1 Parent(s): 98bf65a

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