tuskbyte commited on
Commit
9fb7435
1 Parent(s): 9e294e4

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 41
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "g",
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 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "g",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "41": {
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
+ "ignore_mismatched_sizes": true,
23
+ "is_uroman": false,
24
+ "language": "nld",
25
+ "model_max_length": 1000000000000000019884624838656,
26
+ "normalize": true,
27
+ "pad_token": "g",
28
+ "phonemize": false,
29
+ "tokenizer_class": "VitsTokenizer",
30
+ "unk_token": "<unk>",
31
+ "verbose": false
32
+ }
vocab.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 22,
3
+ "'": 37,
4
+ "-": 2,
5
+ "_": 6,
6
+ "a": 32,
7
+ "b": 18,
8
+ "c": 29,
9
+ "d": 35,
10
+ "e": 40,
11
+ "f": 33,
12
+ "g": 0,
13
+ "h": 11,
14
+ "i": 5,
15
+ "j": 10,
16
+ "k": 23,
17
+ "l": 24,
18
+ "m": 15,
19
+ "n": 20,
20
+ "o": 27,
21
+ "p": 28,
22
+ "q": 7,
23
+ "r": 31,
24
+ "s": 1,
25
+ "t": 38,
26
+ "u": 21,
27
+ "v": 8,
28
+ "w": 9,
29
+ "x": 39,
30
+ "y": 13,
31
+ "z": 16,
32
+ "á": 30,
33
+ "ä": 34,
34
+ "è": 14,
35
+ "é": 19,
36
+ "ë": 25,
37
+ "í": 26,
38
+ "ï": 17,
39
+ "ó": 4,
40
+ "ú": 36,
41
+ "ü": 12,
42
+ "–": 3
43
+ }