sanchit-gandhi HF staff commited on
Commit
5678e3a
1 Parent(s): 2195dc4

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": "hun",
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
+ " ": 10,
3
+ "-": 4,
4
+ "_": 28,
5
+ "a": 19,
6
+ "b": 11,
7
+ "c": 26,
8
+ "d": 12,
9
+ "e": 5,
10
+ "f": 35,
11
+ "g": 27,
12
+ "h": 14,
13
+ "i": 7,
14
+ "j": 20,
15
+ "k": 6,
16
+ "l": 2,
17
+ "m": 33,
18
+ "n": 17,
19
+ "o": 24,
20
+ "p": 16,
21
+ "r": 0,
22
+ "s": 32,
23
+ "t": 1,
24
+ "u": 22,
25
+ "v": 25,
26
+ "x": 31,
27
+ "y": 8,
28
+ "z": 15,
29
+ "á": 29,
30
+ "é": 13,
31
+ "í": 9,
32
+ "ó": 3,
33
+ "ö": 18,
34
+ "ú": 30,
35
+ "ü": 23,
36
+ "ő": 21,
37
+ "ű": 34,
38
+ "–": 36
39
+ }