sanchit-gandhi HF staff commited on
Commit
5161eb8
1 Parent(s): 97bd3f1

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 +44 -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": "ury",
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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 28,
3
+ "'": 17,
4
+ "-": 0,
5
+ "0": 27,
6
+ "1": 6,
7
+ "2": 32,
8
+ "3": 9,
9
+ "4": 37,
10
+ "5": 20,
11
+ "6": 19,
12
+ "7": 33,
13
+ "8": 1,
14
+ "9": 3,
15
+ "_": 38,
16
+ "a": 25,
17
+ "b": 11,
18
+ "c": 39,
19
+ "d": 7,
20
+ "e": 35,
21
+ "f": 30,
22
+ "g": 29,
23
+ "h": 22,
24
+ "i": 15,
25
+ "j": 41,
26
+ "k": 31,
27
+ "l": 16,
28
+ "m": 24,
29
+ "n": 21,
30
+ "o": 14,
31
+ "p": 40,
32
+ "r": 13,
33
+ "s": 5,
34
+ "t": 34,
35
+ "u": 18,
36
+ "w": 10,
37
+ "y": 23,
38
+ "z": 4,
39
+ "ë": 8,
40
+ "ï": 2,
41
+ "–": 12,
42
+ "—": 36,
43
+ "ꞌ": 26
44
+ }