sanchit-gandhi commited on
Commit
7628a4b
·
1 Parent(s): acc5a82

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 +32 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "a",
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": "aka",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "a",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 8,
3
+ "'": 5,
4
+ "-": 3,
5
+ "2": 23,
6
+ "3": 7,
7
+ "_": 6,
8
+ "a": 0,
9
+ "b": 29,
10
+ "d": 28,
11
+ "e": 24,
12
+ "f": 15,
13
+ "g": 17,
14
+ "h": 20,
15
+ "i": 26,
16
+ "k": 19,
17
+ "l": 21,
18
+ "m": 10,
19
+ "n": 4,
20
+ "o": 16,
21
+ "p": 9,
22
+ "r": 25,
23
+ "s": 22,
24
+ "t": 2,
25
+ "u": 18,
26
+ "w": 12,
27
+ "y": 13,
28
+ "á": 11,
29
+ "ɔ": 27,
30
+ "ɛ": 14,
31
+ "ʼ": 1
32
+ }