sanchit-gandhi HF staff commited on
Commit
fa3da15
1 Parent(s): 78c7d3f

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 +27 -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": "bgt",
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 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 0,
3
+ "'": 1,
4
+ "_": 21,
5
+ "a": 3,
6
+ "b": 20,
7
+ "c": 11,
8
+ "d": 24,
9
+ "e": 6,
10
+ "f": 23,
11
+ "g": 15,
12
+ "h": 17,
13
+ "i": 9,
14
+ "j": 10,
15
+ "k": 12,
16
+ "l": 18,
17
+ "m": 5,
18
+ "n": 13,
19
+ "o": 2,
20
+ "p": 4,
21
+ "r": 14,
22
+ "s": 16,
23
+ "t": 19,
24
+ "u": 8,
25
+ "v": 22,
26
+ "w": 7
27
+ }