sanchit-gandhi HF staff commited on
Commit
ec7e8e1
1 Parent(s): d87030b

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