sanchit-gandhi HF staff commited on
Commit
1715190
1 Parent(s): 14f5263

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