vbrydik commited on
Commit
955160e
1 Parent(s): c741261

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 39
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "|",
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": "|",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "39": {
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": "ukr",
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 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 38,
3
+ "'": 33,
4
+ "-": 37,
5
+ "|": 0,
6
+ "а": 2,
7
+ "б": 17,
8
+ "в": 4,
9
+ "г": 20,
10
+ "д": 11,
11
+ "е": 9,
12
+ "ж": 25,
13
+ "з": 19,
14
+ "и": 3,
15
+ "й": 21,
16
+ "к": 16,
17
+ "л": 12,
18
+ "м": 14,
19
+ "н": 5,
20
+ "о": 1,
21
+ "п": 15,
22
+ "р": 10,
23
+ "с": 8,
24
+ "т": 7,
25
+ "у": 13,
26
+ "ф": 34,
27
+ "х": 23,
28
+ "ц": 31,
29
+ "ч": 24,
30
+ "ш": 28,
31
+ "щ": 26,
32
+ "ь": 22,
33
+ "ю": 27,
34
+ "я": 18,
35
+ "є": 30,
36
+ "і": 6,
37
+ "ї": 29,
38
+ "ґ": 36,
39
+ "‐": 35,
40
+ "—": 32
41
+ }