sanchit-gandhi HF staff commited on
Commit
a08f99d
1 Parent(s): 0569928

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": "x",
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": "kog",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "x",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 31,
3
+ "'": 1,
4
+ "0": 23,
5
+ "1": 27,
6
+ "2": 19,
7
+ "3": 16,
8
+ "4": 22,
9
+ "5": 36,
10
+ "6": 32,
11
+ "7": 40,
12
+ "8": 34,
13
+ "9": 44,
14
+ "_": 3,
15
+ "a": 9,
16
+ "b": 39,
17
+ "c": 2,
18
+ "d": 6,
19
+ "e": 30,
20
+ "g": 8,
21
+ "h": 29,
22
+ "i": 10,
23
+ "j": 35,
24
+ "k": 43,
25
+ "l": 5,
26
+ "m": 37,
27
+ "n": 26,
28
+ "o": 14,
29
+ "p": 12,
30
+ "s": 24,
31
+ "t": 33,
32
+ "u": 28,
33
+ "w": 38,
34
+ "x": 0,
35
+ "y": 18,
36
+ "z": 20,
37
+ "á": 41,
38
+ "ã": 17,
39
+ "é": 42,
40
+ "í": 7,
41
+ "ñ": 11,
42
+ "ó": 13,
43
+ "ú": 25,
44
+ "ʉ": 4,
45
+ "́": 15,
46
+ "—": 21
47
+ }