sanchit-gandhi HF staff commited on
Commit
953f70d
1 Parent(s): 1015a57

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