sanchit-gandhi HF staff commited on
Commit
80e2619
1 Parent(s): 89e2e0f

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 +47 -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": "uzb-script_cyrillic",
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 44,
3
+ "0": 36,
4
+ "1": 37,
5
+ "2": 38,
6
+ "3": 42,
7
+ "4": 39,
8
+ "5": 43,
9
+ "6": 40,
10
+ "|": 0,
11
+ "а": 1,
12
+ "б": 9,
13
+ "в": 24,
14
+ "г": 8,
15
+ "д": 6,
16
+ "е": 19,
17
+ "ж": 30,
18
+ "з": 16,
19
+ "и": 2,
20
+ "й": 20,
21
+ "к": 15,
22
+ "л": 4,
23
+ "м": 11,
24
+ "н": 3,
25
+ "о": 7,
26
+ "п": 28,
27
+ "р": 5,
28
+ "с": 13,
29
+ "т": 12,
30
+ "у": 10,
31
+ "ф": 31,
32
+ "х": 23,
33
+ "ч": 22,
34
+ "ш": 18,
35
+ "ъ": 35,
36
+ "ь": 41,
37
+ "э": 25,
38
+ "ю": 34,
39
+ "я": 27,
40
+ "ё": 26,
41
+ "ў": 17,
42
+ "ғ": 29,
43
+ "қ": 14,
44
+ "ҳ": 21,
45
+ "–": 32,
46
+ "—": 33
47
+ }