sanchit-gandhi HF staff commited on
Commit
511374f
1 Parent(s): bd49bf6

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