sanchit-gandhi HF staff commited on
Commit
c4222dc
1 Parent(s): 10b7d02

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