sanchit-gandhi commited on
Commit
0f0c9ea
·
1 Parent(s): 84cf339

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