sanchit-gandhi HF staff commited on
Commit
a17e739
1 Parent(s): 47f1475

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