Simonlob commited on
Commit
f7793da
1 Parent(s): d426f46

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 38
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "ж",
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": "ж",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "38": {
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": "kir",
24
+ "model_max_length": 1000000000000000019884624838656,
25
+ "normalize": true,
26
+ "pad_token": "ж",
27
+ "phonemize": false,
28
+ "tokenizer_class": "VitsTokenizer",
29
+ "unk_token": "<unk>",
30
+ "verbose": false
31
+ }
vocab.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 14,
3
+ "-": 13,
4
+ "_": 16,
5
+ "а": 19,
6
+ "б": 30,
7
+ "в": 31,
8
+ "г": 35,
9
+ "д": 20,
10
+ "е": 8,
11
+ "ж": 0,
12
+ "з": 27,
13
+ "и": 4,
14
+ "й": 10,
15
+ "к": 26,
16
+ "л": 11,
17
+ "м": 36,
18
+ "н": 23,
19
+ "о": 9,
20
+ "п": 32,
21
+ "р": 24,
22
+ "с": 22,
23
+ "т": 21,
24
+ "у": 12,
25
+ "ф": 37,
26
+ "х": 28,
27
+ "ц": 1,
28
+ "ч": 33,
29
+ "ш": 25,
30
+ "ы": 5,
31
+ "ь": 34,
32
+ "э": 18,
33
+ "ю": 6,
34
+ "я": 7,
35
+ "ё": 29,
36
+ "ң": 17,
37
+ "ү": 15,
38
+ "ө": 2,
39
+ "–": 3
40
+ }