sanchit-gandhi HF staff commited on
Commit
861617e
1 Parent(s): b0bf9ee

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": "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": "cek",
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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 35,
3
+ "'": 9,
4
+ "-": 33,
5
+ "0": 25,
6
+ "1": 18,
7
+ "2": 22,
8
+ "3": 12,
9
+ "_": 27,
10
+ "a": 16,
11
+ "b": 5,
12
+ "c": 28,
13
+ "d": 24,
14
+ "e": 19,
15
+ "f": 7,
16
+ "g": 8,
17
+ "h": 15,
18
+ "i": 32,
19
+ "j": 6,
20
+ "k": 3,
21
+ "l": 31,
22
+ "m": 23,
23
+ "n": 4,
24
+ "o": 29,
25
+ "p": 11,
26
+ "q": 1,
27
+ "r": 0,
28
+ "s": 14,
29
+ "t": 26,
30
+ "u": 34,
31
+ "v": 36,
32
+ "w": 17,
33
+ "x": 2,
34
+ "y": 30,
35
+ "z": 10,
36
+ "ä": 13,
37
+ "ö": 21,
38
+ "ü": 20
39
+ }