sanchit-gandhi commited on
Commit
4d5fd2b
·
1 Parent(s): db388c7

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