sanchit-gandhi HF staff commited on
Commit
d5f1b32
1 Parent(s): 20b46f4

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 +38 -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": "quy",
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 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 29,
3
+ "-": 27,
4
+ "_": 1,
5
+ "a": 0,
6
+ "b": 25,
7
+ "c": 8,
8
+ "d": 12,
9
+ "e": 19,
10
+ "f": 5,
11
+ "g": 3,
12
+ "h": 33,
13
+ "i": 9,
14
+ "j": 11,
15
+ "k": 21,
16
+ "l": 24,
17
+ "m": 17,
18
+ "n": 23,
19
+ "o": 2,
20
+ "p": 22,
21
+ "q": 16,
22
+ "r": 13,
23
+ "s": 4,
24
+ "t": 31,
25
+ "u": 10,
26
+ "v": 20,
27
+ "w": 6,
28
+ "x": 26,
29
+ "y": 32,
30
+ "z": 7,
31
+ "á": 18,
32
+ "é": 30,
33
+ "í": 28,
34
+ "ñ": 15,
35
+ "ó": 14,
36
+ "ú": 35,
37
+ "—": 34
38
+ }