sanchit-gandhi HF staff commited on
Commit
c39f046
1 Parent(s): 1e66439

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