sanchit-gandhi HF staff commited on
Commit
fd6c6b0
1 Parent(s): 2560fc9

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 +50 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "ю",
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": "uig-script_cyrillic",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ю",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 41,
3
+ "-": 30,
4
+ "0": 35,
5
+ "1": 31,
6
+ "2": 33,
7
+ "4": 22,
8
+ "_": 5,
9
+ "­": 2,
10
+ "а": 39,
11
+ "б": 13,
12
+ "в": 42,
13
+ "г": 10,
14
+ "д": 23,
15
+ "е": 8,
16
+ "ж": 24,
17
+ "з": 32,
18
+ "и": 44,
19
+ "й": 7,
20
+ "к": 17,
21
+ "л": 15,
22
+ "м": 9,
23
+ "н": 26,
24
+ "о": 21,
25
+ "п": 43,
26
+ "р": 29,
27
+ "с": 16,
28
+ "т": 20,
29
+ "у": 37,
30
+ "ф": 19,
31
+ "х": 4,
32
+ "ц": 28,
33
+ "ч": 12,
34
+ "ш": 27,
35
+ "ъ": 38,
36
+ "ы": 40,
37
+ "ь": 6,
38
+ "ю": 0,
39
+ "я": 18,
40
+ "ё": 11,
41
+ "ғ": 46,
42
+ "җ": 36,
43
+ "қ": 14,
44
+ "ң": 34,
45
+ "ү": 47,
46
+ "һ": 1,
47
+ "ә": 3,
48
+ "ө": 25,
49
+ "—": 45
50
+ }