sanchit-gandhi HF staff commited on
Commit
c3a100e
1 Parent(s): b6f7258

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