sanchit-gandhi HF staff commited on
Commit
c28e86e
1 Parent(s): b61478a

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": "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": "cbt",
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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 28,
3
+ "'": 17,
4
+ "a": 0,
5
+ "b": 27,
6
+ "c": 12,
7
+ "d": 22,
8
+ "e": 24,
9
+ "f": 26,
10
+ "h": 7,
11
+ "i": 3,
12
+ "l": 23,
13
+ "m": 16,
14
+ "n": 1,
15
+ "o": 4,
16
+ "p": 10,
17
+ "q": 15,
18
+ "r": 11,
19
+ "s": 13,
20
+ "t": 6,
21
+ "u": 8,
22
+ "y": 14,
23
+ "|": 2,
24
+ "á": 18,
25
+ "ë": 5,
26
+ "í": 19,
27
+ "ó": 21,
28
+ "́": 25,
29
+ "—": 20,
30
+ "ꞌ": 9
31
+ }