sanchit-gandhi HF staff commited on
Commit
5b49f0e
1 Parent(s): c8d6dd2

Upload tokenizer

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