sanchit-gandhi HF staff commited on
Commit
3c91dba
1 Parent(s): dc12782

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 +39 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "-",
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": "kpq",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "-",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 30,
3
+ "'": 10,
4
+ "-": 0,
5
+ "0": 19,
6
+ "1": 5,
7
+ "2": 24,
8
+ "3": 17,
9
+ "4": 29,
10
+ "5": 32,
11
+ "7": 20,
12
+ "9": 36,
13
+ "_": 6,
14
+ "a": 31,
15
+ "b": 14,
16
+ "c": 35,
17
+ "d": 27,
18
+ "e": 23,
19
+ "f": 4,
20
+ "g": 1,
21
+ "h": 34,
22
+ "i": 15,
23
+ "j": 16,
24
+ "k": 21,
25
+ "l": 8,
26
+ "m": 13,
27
+ "n": 33,
28
+ "o": 2,
29
+ "p": 18,
30
+ "r": 22,
31
+ "s": 11,
32
+ "t": 3,
33
+ "u": 12,
34
+ "w": 25,
35
+ "y": 26,
36
+ "z": 7,
37
+ "́": 28,
38
+ "–": 9
39
+ }