sanchit-gandhi HF staff commited on
Commit
d2ac47e
1 Parent(s): bcb5002

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