sanchit-gandhi HF staff commited on
Commit
bb1eaee
1 Parent(s): e90f374

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 +35 -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": "lsm",
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 32,
3
+ "'": 20,
4
+ "-": 23,
5
+ "0": 25,
6
+ "1": 26,
7
+ "2": 27,
8
+ "3": 30,
9
+ "4": 28,
10
+ "5": 29,
11
+ "a": 0,
12
+ "b": 7,
13
+ "c": 19,
14
+ "d": 15,
15
+ "e": 3,
16
+ "f": 21,
17
+ "g": 18,
18
+ "h": 8,
19
+ "i": 2,
20
+ "j": 22,
21
+ "k": 16,
22
+ "l": 9,
23
+ "m": 10,
24
+ "n": 5,
25
+ "o": 4,
26
+ "p": 24,
27
+ "q": 31,
28
+ "r": 14,
29
+ "s": 12,
30
+ "t": 17,
31
+ "u": 6,
32
+ "w": 13,
33
+ "y": 11,
34
+ "|": 1
35
+ }