sanchit-gandhi commited on
Commit
20fb04c
·
1 Parent(s): 5adf2aa

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