sanchit-gandhi HF staff commited on
Commit
ae9190c
1 Parent(s): 3d7ae86

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 +29 -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": "sus",
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 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 26,
3
+ "-": 25,
4
+ "a": 1,
5
+ "b": 10,
6
+ "d": 19,
7
+ "e": 5,
8
+ "f": 17,
9
+ "g": 21,
10
+ "h": 23,
11
+ "i": 3,
12
+ "k": 18,
13
+ "l": 12,
14
+ "m": 6,
15
+ "n": 2,
16
+ "o": 11,
17
+ "p": 24,
18
+ "r": 8,
19
+ "s": 14,
20
+ "t": 16,
21
+ "u": 9,
22
+ "w": 20,
23
+ "x": 4,
24
+ "y": 15,
25
+ "|": 0,
26
+ "ɔ": 13,
27
+ "ɛ": 7,
28
+ "ɲ": 22
29
+ }