sanchit-gandhi HF staff commited on
Commit
38d25bf
1 Parent(s): f1f8761

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 +33 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "i",
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": "plw",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "i",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 7,
3
+ "'": 6,
4
+ "-": 11,
5
+ "0": 29,
6
+ "1": 10,
7
+ "2": 19,
8
+ "3": 2,
9
+ "4": 8,
10
+ "6": 4,
11
+ "_": 27,
12
+ "a": 1,
13
+ "b": 22,
14
+ "d": 20,
15
+ "e": 24,
16
+ "g": 21,
17
+ "h": 13,
18
+ "i": 0,
19
+ "j": 26,
20
+ "k": 15,
21
+ "l": 28,
22
+ "m": 25,
23
+ "n": 14,
24
+ "o": 30,
25
+ "p": 9,
26
+ "r": 18,
27
+ "s": 23,
28
+ "t": 3,
29
+ "u": 16,
30
+ "w": 12,
31
+ "y": 17,
32
+ "ʼ": 5
33
+ }