thomasht86 commited on
Commit
307340a
1 Parent(s): 645bc0c

Upload tokenizer

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