sanchit-gandhi HF staff commited on
Commit
da65875
1 Parent(s): 6a024cf

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 +48 -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": "pol",
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 2,
3
+ "-": 24,
4
+ "0": 4,
5
+ "1": 18,
6
+ "2": 12,
7
+ "3": 39,
8
+ "4": 15,
9
+ "5": 30,
10
+ "6": 23,
11
+ "7": 40,
12
+ "8": 27,
13
+ "9": 20,
14
+ "_": 31,
15
+ "a": 29,
16
+ "b": 26,
17
+ "c": 5,
18
+ "d": 11,
19
+ "e": 22,
20
+ "f": 17,
21
+ "g": 16,
22
+ "h": 1,
23
+ "i": 35,
24
+ "j": 37,
25
+ "k": 25,
26
+ "l": 3,
27
+ "m": 6,
28
+ "n": 41,
29
+ "o": 38,
30
+ "p": 19,
31
+ "r": 28,
32
+ "s": 8,
33
+ "t": 42,
34
+ "u": 10,
35
+ "w": 0,
36
+ "y": 33,
37
+ "z": 9,
38
+ "ó": 14,
39
+ "ą": 7,
40
+ "ć": 44,
41
+ "ę": 32,
42
+ "ł": 34,
43
+ "ń": 13,
44
+ "ś": 43,
45
+ "ź": 45,
46
+ "ż": 36,
47
+ "—": 21
48
+ }