sanchit-gandhi HF staff commited on
Commit
a37e809
1 Parent(s): 1907294

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