sanchit-gandhi HF staff commited on
Commit
07e9aec
1 Parent(s): dae467a

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 +42 -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": "bpr",
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 39,
3
+ "'": 32,
4
+ "-": 27,
5
+ "0": 29,
6
+ "1": 30,
7
+ "2": 31,
8
+ "3": 34,
9
+ "4": 33,
10
+ "5": 38,
11
+ "7": 35,
12
+ "8": 36,
13
+ "a": 1,
14
+ "b": 16,
15
+ "c": 37,
16
+ "d": 3,
17
+ "e": 10,
18
+ "f": 15,
19
+ "g": 9,
20
+ "h": 21,
21
+ "i": 4,
22
+ "k": 11,
23
+ "l": 6,
24
+ "m": 8,
25
+ "n": 2,
26
+ "o": 12,
27
+ "p": 26,
28
+ "r": 23,
29
+ "s": 13,
30
+ "t": 7,
31
+ "u": 5,
32
+ "w": 18,
33
+ "y": 14,
34
+ "|": 0,
35
+ "à": 19,
36
+ "è": 20,
37
+ "é": 17,
38
+ "ê": 25,
39
+ "ì": 28,
40
+ "ò": 22,
41
+ "ù": 24
42
+ }