jonathansuru commited on
Commit
aebb236
1 Parent(s): 88bd42e

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 46
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "_",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "unk_token": {
10
+ "content": "<unk>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "_",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "46": {
13
+ "content": "<unk>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "clean_up_tokenization_spaces": true,
22
+ "is_uroman": false,
23
+ "language": "fon",
24
+ "model_max_length": 1000000000000000019884624838656,
25
+ "normalize": true,
26
+ "pad_token": "_",
27
+ "phonemize": false,
28
+ "tokenizer_class": "VitsTokenizer",
29
+ "unk_token": "<unk>",
30
+ "verbose": false
31
+ }
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
+ }