sanchit-gandhi HF staff commited on
Commit
93d1a56
1 Parent(s): eb1f7de

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