sanchit-gandhi HF staff commited on
Commit
528e83c
1 Parent(s): ea83570

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