sanchit-gandhi HF staff commited on
Commit
6d10dd9
1 Parent(s): f40c8d4

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