sanchit-gandhi HF staff commited on
Commit
244afba
1 Parent(s): 01484dc

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