sanchit-gandhi HF staff commited on
Commit
1bdda41
1 Parent(s): 106dd5a

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