sanchit-gandhi HF staff commited on
Commit
99e4d04
1 Parent(s): f432141

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": "0",
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": "gwi",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "0",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 28,
3
+ "'": 11,
4
+ "-": 18,
5
+ "0": 0,
6
+ "1": 42,
7
+ "2": 7,
8
+ "3": 8,
9
+ "4": 1,
10
+ "5": 40,
11
+ "6": 41,
12
+ "7": 34,
13
+ "8": 5,
14
+ "9": 2,
15
+ "_": 24,
16
+ "a": 12,
17
+ "b": 33,
18
+ "c": 9,
19
+ "d": 29,
20
+ "e": 44,
21
+ "f": 16,
22
+ "g": 25,
23
+ "h": 45,
24
+ "i": 22,
25
+ "j": 10,
26
+ "k": 19,
27
+ "l": 21,
28
+ "m": 39,
29
+ "n": 35,
30
+ "o": 26,
31
+ "p": 4,
32
+ "q": 15,
33
+ "r": 17,
34
+ "s": 23,
35
+ "t": 20,
36
+ "u": 27,
37
+ "v": 6,
38
+ "w": 31,
39
+ "x": 36,
40
+ "y": 37,
41
+ "z": 38,
42
+ "ą": 14,
43
+ "ę": 43,
44
+ "į": 13,
45
+ "ł": 32,
46
+ "ų": 3,
47
+ "ǫ": 30
48
+ }