sanchit-gandhi HF staff commited on
Commit
abbd97a
1 Parent(s): ae6885c

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 +41 -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": "ukr",
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 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 38,
3
+ "'": 33,
4
+ "-": 37,
5
+ "|": 0,
6
+ "а": 2,
7
+ "б": 17,
8
+ "в": 4,
9
+ "г": 20,
10
+ "д": 11,
11
+ "е": 9,
12
+ "ж": 25,
13
+ "з": 19,
14
+ "и": 3,
15
+ "й": 21,
16
+ "к": 16,
17
+ "л": 12,
18
+ "м": 14,
19
+ "н": 5,
20
+ "о": 1,
21
+ "п": 15,
22
+ "р": 10,
23
+ "с": 8,
24
+ "т": 7,
25
+ "у": 13,
26
+ "ф": 34,
27
+ "х": 23,
28
+ "ц": 31,
29
+ "ч": 24,
30
+ "ш": 28,
31
+ "щ": 26,
32
+ "ь": 22,
33
+ "ю": 27,
34
+ "я": 18,
35
+ "є": 30,
36
+ "і": 6,
37
+ "ї": 29,
38
+ "ґ": 36,
39
+ "‐": 35,
40
+ "—": 32
41
+ }