Sigurdur commited on
Commit
8133b2b
·
verified ·
1 Parent(s): 8176c72

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 43
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "5",
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": "5",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "43": {
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
+ "extra_special_tokens": {},
23
+ "is_uroman": false,
24
+ "language": "isl",
25
+ "model_max_length": 1000000000000000019884624838656,
26
+ "normalize": true,
27
+ "pad_token": "5",
28
+ "phonemize": false,
29
+ "tokenizer_class": "VitsTokenizer",
30
+ "unk_token": "<unk>",
31
+ "verbose": false
32
+ }
vocab.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 2,
3
+ "-": 25,
4
+ "0": 24,
5
+ "1": 33,
6
+ "2": 17,
7
+ "3": 14,
8
+ "5": 0,
9
+ "7": 26,
10
+ "8": 36,
11
+ "_": 10,
12
+ "a": 9,
13
+ "b": 37,
14
+ "d": 31,
15
+ "e": 11,
16
+ "f": 3,
17
+ "g": 15,
18
+ "h": 38,
19
+ "i": 29,
20
+ "j": 41,
21
+ "k": 6,
22
+ "l": 5,
23
+ "m": 16,
24
+ "n": 30,
25
+ "o": 8,
26
+ "p": 19,
27
+ "r": 27,
28
+ "s": 28,
29
+ "t": 39,
30
+ "u": 18,
31
+ "v": 23,
32
+ "x": 22,
33
+ "y": 35,
34
+ "á": 13,
35
+ "æ": 21,
36
+ "é": 20,
37
+ "í": 34,
38
+ "ð": 4,
39
+ "ó": 7,
40
+ "ö": 42,
41
+ "ú": 12,
42
+ "ý": 32,
43
+ "þ": 40,
44
+ "–": 1
45
+ }