sanchit-gandhi commited on
Commit
5277588
·
1 Parent(s): c38e770

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": " ",
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": "vid",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": " ",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 0,
3
+ "'": 23,
4
+ "_": 4,
5
+ "a": 7,
6
+ "b": 21,
7
+ "c": 9,
8
+ "d": 12,
9
+ "e": 3,
10
+ "f": 11,
11
+ "g": 6,
12
+ "h": 24,
13
+ "i": 14,
14
+ "j": 13,
15
+ "k": 15,
16
+ "l": 19,
17
+ "m": 1,
18
+ "n": 10,
19
+ "o": 22,
20
+ "p": 20,
21
+ "s": 18,
22
+ "t": 5,
23
+ "u": 16,
24
+ "v": 17,
25
+ "w": 8,
26
+ "y": 25,
27
+ "z": 2
28
+ }