sanchit-gandhi HF staff commited on
Commit
50ba29e
1 Parent(s): e4165e8

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 +38 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "r",
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": "ikk",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "r",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 11,
3
+ "'": 2,
4
+ "-": 8,
5
+ "_": 22,
6
+ "a": 3,
7
+ "b": 9,
8
+ "c": 19,
9
+ "d": 28,
10
+ "e": 18,
11
+ "f": 31,
12
+ "g": 27,
13
+ "h": 4,
14
+ "i": 12,
15
+ "j": 34,
16
+ "k": 5,
17
+ "l": 24,
18
+ "m": 16,
19
+ "n": 6,
20
+ "o": 17,
21
+ "p": 32,
22
+ "r": 0,
23
+ "s": 20,
24
+ "t": 1,
25
+ "u": 30,
26
+ "v": 26,
27
+ "w": 13,
28
+ "y": 21,
29
+ "z": 23,
30
+ "ò": 25,
31
+ "ù": 14,
32
+ "̀": 15,
33
+ "ṅ": 33,
34
+ "ẹ": 29,
35
+ "ị": 10,
36
+ "ọ": 35,
37
+ "ụ": 7
38
+ }