sanchit-gandhi HF staff commited on
Commit
4bf7b94
1 Parent(s): 9bd8bcf

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 +51 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "g",
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": "bfo",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "g",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 30,
3
+ "-": 29,
4
+ "1": 17,
5
+ "_": 27,
6
+ "a": 44,
7
+ "b": 45,
8
+ "c": 26,
9
+ "d": 12,
10
+ "e": 34,
11
+ "f": 22,
12
+ "g": 0,
13
+ "h": 35,
14
+ "i": 31,
15
+ "j": 1,
16
+ "k": 10,
17
+ "l": 46,
18
+ "m": 13,
19
+ "n": 21,
20
+ "o": 18,
21
+ "p": 19,
22
+ "r": 16,
23
+ "s": 3,
24
+ "t": 20,
25
+ "u": 6,
26
+ "v": 11,
27
+ "w": 8,
28
+ "y": 37,
29
+ "á": 36,
30
+ "ã": 43,
31
+ "é": 25,
32
+ "õ": 9,
33
+ "ú": 15,
34
+ "ĩ": 38,
35
+ "ı": 48,
36
+ "ŋ": 33,
37
+ "ũ": 24,
38
+ "ƴ": 42,
39
+ "ɓ": 47,
40
+ "ɛ": 28,
41
+ "ɩ": 40,
42
+ "ʋ": 7,
43
+ "ʻ": 4,
44
+ "ʼ": 32,
45
+ "́": 14,
46
+ "̃": 39,
47
+ "ẽ": 2,
48
+ "—": 23,
49
+ "ↄ": 41,
50
+ "ꞌ": 5
51
+ }