sanchit-gandhi HF staff commited on
Commit
962716f
1 Parent(s): 8019d4e

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 +50 -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": "kjb",
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 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 47,
3
+ "'": 10,
4
+ "-": 33,
5
+ "0": 36,
6
+ "1": 37,
7
+ "2": 38,
8
+ "3": 41,
9
+ "4": 39,
10
+ "5": 40,
11
+ "6": 43,
12
+ "7": 44,
13
+ "8": 45,
14
+ "9": 42,
15
+ "a": 1,
16
+ "b": 13,
17
+ "c": 5,
18
+ "d": 23,
19
+ "e": 7,
20
+ "f": 32,
21
+ "g": 27,
22
+ "h": 17,
23
+ "i": 2,
24
+ "j": 11,
25
+ "k": 15,
26
+ "l": 6,
27
+ "m": 16,
28
+ "n": 3,
29
+ "o": 9,
30
+ "p": 20,
31
+ "q": 25,
32
+ "r": 22,
33
+ "s": 18,
34
+ "t": 4,
35
+ "u": 12,
36
+ "v": 35,
37
+ "w": 19,
38
+ "x": 14,
39
+ "y": 8,
40
+ "z": 21,
41
+ "|": 0,
42
+ "á": 31,
43
+ "é": 30,
44
+ "í": 29,
45
+ "ñ": 46,
46
+ "ó": 34,
47
+ "ú": 26,
48
+ "ẍ": 24,
49
+ "—": 28
50
+ }