sanchit-gandhi HF staff commited on
Commit
2e4a5de
1 Parent(s): 1dc350c

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