sanchit-gandhi HF staff commited on
Commit
846e59e
1 Parent(s): 103455a

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 +47 -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": "deu",
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 0,
3
+ "-": 5,
4
+ "0": 44,
5
+ "1": 7,
6
+ "2": 2,
7
+ "3": 13,
8
+ "4": 11,
9
+ "5": 31,
10
+ "6": 30,
11
+ "7": 42,
12
+ "8": 8,
13
+ "_": 27,
14
+ "a": 9,
15
+ "b": 22,
16
+ "c": 33,
17
+ "d": 21,
18
+ "e": 38,
19
+ "f": 6,
20
+ "g": 4,
21
+ "h": 10,
22
+ "i": 34,
23
+ "j": 28,
24
+ "k": 37,
25
+ "l": 17,
26
+ "m": 15,
27
+ "n": 18,
28
+ "o": 25,
29
+ "p": 36,
30
+ "q": 3,
31
+ "r": 14,
32
+ "s": 29,
33
+ "t": 19,
34
+ "u": 26,
35
+ "v": 1,
36
+ "w": 40,
37
+ "x": 43,
38
+ "y": 23,
39
+ "z": 41,
40
+ "ß": 24,
41
+ "ä": 16,
42
+ "ë": 20,
43
+ "ï": 32,
44
+ "ö": 12,
45
+ "ü": 35,
46
+ "–": 39
47
+ }