sanchit-gandhi HF staff commited on
Commit
1d90ea8
1 Parent(s): acd8129

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": "|",
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": "cnt",
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 44,
3
+ "'": 3,
4
+ "-": 36,
5
+ "1": 17,
6
+ "2": 1,
7
+ "3": 10,
8
+ "4": 8,
9
+ "5": 9,
10
+ "a": 2,
11
+ "b": 29,
12
+ "c": 14,
13
+ "d": 20,
14
+ "e": 12,
15
+ "f": 37,
16
+ "g": 11,
17
+ "h": 31,
18
+ "i": 4,
19
+ "j": 6,
20
+ "k": 41,
21
+ "l": 18,
22
+ "m": 22,
23
+ "n": 5,
24
+ "o": 19,
25
+ "p": 34,
26
+ "q": 25,
27
+ "r": 30,
28
+ "s": 13,
29
+ "t": 23,
30
+ "u": 7,
31
+ "v": 38,
32
+ "x": 42,
33
+ "y": 40,
34
+ "z": 39,
35
+ "|": 0,
36
+ "á": 15,
37
+ "é": 27,
38
+ "ë": 21,
39
+ "í": 33,
40
+ "ñ": 43,
41
+ "ó": 26,
42
+ "ú": 32,
43
+ "ü": 35,
44
+ "ŋ": 28,
45
+ "ɨ": 16,
46
+ "́": 24
47
+ }