sanchit-gandhi HF staff commited on
Commit
95525a2
1 Parent(s): 4189f8e

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 +37 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "i",
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": "kij",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "i",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 24,
3
+ "'": 28,
4
+ "-": 13,
5
+ "0": 1,
6
+ "1": 15,
7
+ "2": 22,
8
+ "4": 34,
9
+ "5": 21,
10
+ "6": 3,
11
+ "8": 18,
12
+ "_": 14,
13
+ "`": 30,
14
+ "a": 29,
15
+ "b": 19,
16
+ "d": 6,
17
+ "e": 12,
18
+ "f": 23,
19
+ "g": 10,
20
+ "i": 0,
21
+ "k": 9,
22
+ "l": 25,
23
+ "m": 31,
24
+ "n": 17,
25
+ "o": 27,
26
+ "p": 16,
27
+ "r": 20,
28
+ "s": 11,
29
+ "t": 7,
30
+ "u": 33,
31
+ "v": 26,
32
+ "w": 4,
33
+ "y": 5,
34
+ "á": 2,
35
+ "é": 8,
36
+ "ó": 32
37
+ }