sanchit-gandhi HF staff commited on
Commit
3f3a400
1 Parent(s): a5fad30

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": "|",
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": "suk",
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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 36,
3
+ "'": 20,
4
+ "-": 27,
5
+ "0": 32,
6
+ "1": 33,
7
+ "2": 34,
8
+ "a": 1,
9
+ "b": 10,
10
+ "c": 25,
11
+ "d": 21,
12
+ "e": 7,
13
+ "f": 24,
14
+ "g": 6,
15
+ "h": 13,
16
+ "i": 8,
17
+ "j": 19,
18
+ "k": 11,
19
+ "l": 4,
20
+ "m": 14,
21
+ "n": 2,
22
+ "o": 9,
23
+ "p": 23,
24
+ "s": 17,
25
+ "t": 18,
26
+ "u": 16,
27
+ "v": 28,
28
+ "w": 12,
29
+ "y": 15,
30
+ "z": 22,
31
+ "|": 0,
32
+ "à": 30,
33
+ "è": 31,
34
+ "ì": 35,
35
+ "ò": 26,
36
+ "ó": 29,
37
+ "ī": 5,
38
+ "ū": 3
39
+ }