sanchit-gandhi HF staff commited on
Commit
ff38bde
1 Parent(s): 9e5c953

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