sanchit-gandhi HF staff commited on
Commit
868a007
1 Parent(s): 337afdf

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 +50 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "f",
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": "muy",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "f",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 16,
3
+ "-": 21,
4
+ "_": 14,
5
+ "a": 26,
6
+ "b": 41,
7
+ "c": 34,
8
+ "d": 3,
9
+ "e": 7,
10
+ "f": 0,
11
+ "g": 23,
12
+ "h": 27,
13
+ "i": 36,
14
+ "j": 15,
15
+ "k": 6,
16
+ "l": 9,
17
+ "m": 37,
18
+ "n": 45,
19
+ "o": 10,
20
+ "p": 44,
21
+ "r": 38,
22
+ "s": 30,
23
+ "t": 18,
24
+ "u": 42,
25
+ "v": 47,
26
+ "w": 40,
27
+ "y": 28,
28
+ "z": 17,
29
+ "à": 11,
30
+ "á": 33,
31
+ "â": 43,
32
+ "è": 1,
33
+ "é": 8,
34
+ "ê": 22,
35
+ "ì": 5,
36
+ "í": 29,
37
+ "î": 20,
38
+ "ò": 32,
39
+ "ô": 24,
40
+ "ù": 12,
41
+ "ú": 46,
42
+ "ŋ": 31,
43
+ "ɓ": 19,
44
+ "ɗ": 35,
45
+ "ə": 2,
46
+ "ʉ": 39,
47
+ "̀": 13,
48
+ "́": 25,
49
+ "̂": 4
50
+ }