sanchit-gandhi HF staff commited on
Commit
2482330
1 Parent(s): efc800b

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 +48 -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": "fon",
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 17,
3
+ "'": 16,
4
+ "-": 7,
5
+ "_": 0,
6
+ "a": 22,
7
+ "b": 27,
8
+ "c": 40,
9
+ "d": 6,
10
+ "e": 9,
11
+ "f": 8,
12
+ "g": 15,
13
+ "h": 24,
14
+ "i": 25,
15
+ "j": 32,
16
+ "k": 20,
17
+ "l": 34,
18
+ "m": 30,
19
+ "n": 23,
20
+ "o": 41,
21
+ "p": 29,
22
+ "s": 18,
23
+ "t": 5,
24
+ "u": 28,
25
+ "v": 13,
26
+ "w": 42,
27
+ "x": 36,
28
+ "y": 39,
29
+ "z": 38,
30
+ "á": 31,
31
+ "è": 1,
32
+ "é": 12,
33
+ "ì": 43,
34
+ "í": 26,
35
+ "ó": 10,
36
+ "ú": 11,
37
+ "đ": 33,
38
+ "ě": 44,
39
+ "ǎ": 14,
40
+ "ǐ": 4,
41
+ "ǒ": 35,
42
+ "ǔ": 19,
43
+ "ɔ": 37,
44
+ "ɖ": 2,
45
+ "ɛ": 45,
46
+ "́": 21,
47
+ "̌": 3
48
+ }