sanchit-gandhi commited on
Commit
5b72618
·
1 Parent(s): 0a342c8

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 +33 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "f",
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": "beh",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "f",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 15,
3
+ "-": 8,
4
+ "_": 16,
5
+ "a": 24,
6
+ "b": 30,
7
+ "c": 23,
8
+ "d": 13,
9
+ "e": 22,
10
+ "f": 0,
11
+ "g": 18,
12
+ "h": 14,
13
+ "i": 10,
14
+ "k": 7,
15
+ "l": 9,
16
+ "m": 5,
17
+ "n": 29,
18
+ "o": 21,
19
+ "p": 26,
20
+ "r": 11,
21
+ "s": 2,
22
+ "t": 19,
23
+ "u": 4,
24
+ "w": 12,
25
+ "y": 17,
26
+ "á": 1,
27
+ "é": 3,
28
+ "í": 25,
29
+ "ó": 6,
30
+ "ú": 28,
31
+ "ǝ": 27,
32
+ "́": 20
33
+ }