sanchit-gandhi HF staff commited on
Commit
bd63f27
1 Parent(s): f1f8a61

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 +42 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "ó",
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": "moz",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ó",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 13,
3
+ "-": 2,
4
+ "_": 6,
5
+ "a": 17,
6
+ "b": 7,
7
+ "c": 31,
8
+ "d": 29,
9
+ "e": 32,
10
+ "g": 36,
11
+ "h": 10,
12
+ "i": 38,
13
+ "j": 9,
14
+ "k": 34,
15
+ "l": 16,
16
+ "m": 26,
17
+ "n": 18,
18
+ "o": 39,
19
+ "p": 30,
20
+ "r": 27,
21
+ "s": 24,
22
+ "t": 25,
23
+ "u": 3,
24
+ "w": 8,
25
+ "y": 37,
26
+ "z": 20,
27
+ "á": 21,
28
+ "â": 14,
29
+ "í": 35,
30
+ "î": 22,
31
+ "ó": 0,
32
+ "ô": 28,
33
+ "ú": 19,
34
+ "û": 15,
35
+ "ŋ": 23,
36
+ "ƴ": 11,
37
+ "ɓ": 5,
38
+ "ɗ": 1,
39
+ "ʼ": 33,
40
+ "̰": 4,
41
+ "—": 12
42
+ }