sanchit-gandhi HF staff commited on
Commit
163c31e
1 Parent(s): af2a764

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 +46 -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": "gyr",
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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 43,
3
+ "'": 12,
4
+ "-": 35,
5
+ "a": 2,
6
+ "b": 17,
7
+ "c": 22,
8
+ "d": 19,
9
+ "e": 1,
10
+ "f": 37,
11
+ "g": 21,
12
+ "h": 24,
13
+ "i": 5,
14
+ "j": 27,
15
+ "k": 11,
16
+ "l": 29,
17
+ "m": 14,
18
+ "n": 16,
19
+ "o": 3,
20
+ "p": 6,
21
+ "q": 41,
22
+ "r": 4,
23
+ "s": 7,
24
+ "t": 13,
25
+ "u": 9,
26
+ "v": 8,
27
+ "w": 18,
28
+ "x": 42,
29
+ "y": 15,
30
+ "z": 40,
31
+ "|": 0,
32
+ "á": 39,
33
+ "ä": 20,
34
+ "é": 36,
35
+ "ë": 25,
36
+ "í": 33,
37
+ "ï": 32,
38
+ "ñ": 23,
39
+ "ó": 38,
40
+ "ö": 30,
41
+ "ú": 31,
42
+ "ü": 26,
43
+ "ɨ": 10,
44
+ "̇": 28,
45
+ "–": 34
46
+ }