sanchit-gandhi HF staff commited on
Commit
5ce8f25
1 Parent(s): 81ea14a

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