sanchit-gandhi commited on
Commit
f3e3f02
·
1 Parent(s): ae3b789

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 +32 -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": "kby",
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 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 29,
3
+ "'": 19,
4
+ "-": 17,
5
+ "3": 20,
6
+ "4": 22,
7
+ "_": 13,
8
+ "a": 15,
9
+ "b": 18,
10
+ "c": 27,
11
+ "d": 28,
12
+ "e": 11,
13
+ "f": 9,
14
+ "g": 16,
15
+ "h": 2,
16
+ "i": 23,
17
+ "j": 5,
18
+ "k": 6,
19
+ "l": 10,
20
+ "m": 14,
21
+ "n": 4,
22
+ "o": 12,
23
+ "p": 7,
24
+ "r": 24,
25
+ "s": 3,
26
+ "t": 1,
27
+ "u": 21,
28
+ "w": 0,
29
+ "y": 8,
30
+ "ǝ": 25,
31
+ "ɍ": 26
32
+ }