thomasht86
commited on
Commit
•
0af7d02
1
Parent(s):
2616f8c
Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +16 -0
- tokenizer_config.json +47 -0
- vocab.json +41 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"ø": 39
|
3 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": {
|
3 |
+
"content": "x",
|
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 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"38": {
|
21 |
+
"content": "æ",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": false
|
27 |
+
},
|
28 |
+
"39": {
|
29 |
+
"content": "ø",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"clean_up_tokenization_spaces": true,
|
38 |
+
"is_uroman": false,
|
39 |
+
"language": "swe",
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"normalize": true,
|
42 |
+
"pad_token": "x",
|
43 |
+
"phonemize": false,
|
44 |
+
"tokenizer_class": "VitsTokenizer",
|
45 |
+
"unk_token": "<unk>",
|
46 |
+
"verbose": false
|
47 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"æ": 34,
|
37 |
+
"é": 16,
|
38 |
+
"ö": 19,
|
39 |
+
"ø": 19,
|
40 |
+
"–": 6
|
41 |
+
}
|