sanchit-gandhi commited on
Commit
fb258e8
·
1 Parent(s): 9359b6d

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