sanchit-gandhi commited on
Commit
7de4f82
·
1 Parent(s): 0715fb8

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 +31 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "l",
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": "lat",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "l",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 9,
3
+ "-": 13,
4
+ "_": 10,
5
+ "a": 23,
6
+ "b": 2,
7
+ "c": 15,
8
+ "d": 16,
9
+ "e": 28,
10
+ "f": 4,
11
+ "g": 19,
12
+ "h": 17,
13
+ "i": 18,
14
+ "l": 0,
15
+ "m": 24,
16
+ "n": 21,
17
+ "o": 25,
18
+ "p": 1,
19
+ "q": 22,
20
+ "r": 6,
21
+ "s": 7,
22
+ "t": 3,
23
+ "u": 27,
24
+ "v": 12,
25
+ "x": 20,
26
+ "y": 26,
27
+ "z": 5,
28
+ "ì": 14,
29
+ "í": 8,
30
+ "—": 11
31
+ }