sanchit-gandhi HF staff commited on
Commit
77f9ad4
1 Parent(s): 8f55b85

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 +48 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "o",
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": "pps",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "o",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 20,
3
+ "'": 1,
4
+ "-": 35,
5
+ "1": 4,
6
+ "2": 37,
7
+ "5": 40,
8
+ "9": 23,
9
+ "_": 6,
10
+ "`": 11,
11
+ "a": 41,
12
+ "b": 36,
13
+ "c": 26,
14
+ "d": 10,
15
+ "e": 22,
16
+ "f": 29,
17
+ "g": 13,
18
+ "h": 17,
19
+ "i": 14,
20
+ "j": 2,
21
+ "k": 28,
22
+ "l": 24,
23
+ "m": 12,
24
+ "n": 19,
25
+ "o": 0,
26
+ "p": 21,
27
+ "q": 30,
28
+ "r": 3,
29
+ "s": 32,
30
+ "t": 5,
31
+ "u": 18,
32
+ "v": 43,
33
+ "x": 7,
34
+ "y": 34,
35
+ "z": 33,
36
+ "à": 16,
37
+ "á": 42,
38
+ "é": 45,
39
+ "ì": 9,
40
+ "í": 39,
41
+ "ñ": 31,
42
+ "ó": 8,
43
+ "ù": 44,
44
+ "ú": 15,
45
+ "̱": 38,
46
+ "—": 25,
47
+ "ꞌ": 27
48
+ }