sanchit-gandhi HF staff commited on
Commit
53fb6cd
1 Parent(s): 47ecf79

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +4 -0
  2. tokenizer_config.json +12 -0
  3. vocab.json +46 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "ч",
3
+ "unk_token": "<unk>"
4
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "clean_up_tokenization_spaces": true,
4
+ "is_uroman": false,
5
+ "language": "rus",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ч",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 1,
3
+ "-": 39,
4
+ "0": 11,
5
+ "1": 36,
6
+ "2": 10,
7
+ "4": 27,
8
+ "_": 21,
9
+ "c": 20,
10
+ "m": 23,
11
+ "o": 29,
12
+ "q": 32,
13
+ "а": 8,
14
+ "б": 38,
15
+ "в": 41,
16
+ "г": 42,
17
+ "д": 2,
18
+ "е": 37,
19
+ "ж": 16,
20
+ "з": 19,
21
+ "и": 33,
22
+ "й": 5,
23
+ "к": 35,
24
+ "л": 15,
25
+ "м": 43,
26
+ "н": 14,
27
+ "о": 9,
28
+ "п": 22,
29
+ "р": 26,
30
+ "с": 6,
31
+ "т": 40,
32
+ "у": 7,
33
+ "ф": 31,
34
+ "х": 17,
35
+ "ц": 34,
36
+ "ч": 0,
37
+ "ш": 18,
38
+ "щ": 28,
39
+ "ъ": 12,
40
+ "ы": 13,
41
+ "ь": 3,
42
+ "э": 25,
43
+ "ю": 24,
44
+ "я": 4,
45
+ "–": 30
46
+ }