sanchit-gandhi HF staff commited on
Commit
3191f79
1 Parent(s): 2195dc4

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