sanchit-gandhi HF staff commited on
Commit
2935a8e
1 Parent(s): 0c8cb8d

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 +33 -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": "cni",
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 30,
3
+ "'": 20,
4
+ "-": 18,
5
+ "0": 19,
6
+ "1": 21,
7
+ "2": 22,
8
+ "3": 28,
9
+ "4": 24,
10
+ "5": 26,
11
+ "6": 25,
12
+ "7": 23,
13
+ "8": 27,
14
+ "9": 29,
15
+ "a": 0,
16
+ "c": 9,
17
+ "e": 3,
18
+ "h": 15,
19
+ "i": 1,
20
+ "j": 14,
21
+ "m": 13,
22
+ "n": 5,
23
+ "o": 7,
24
+ "p": 10,
25
+ "q": 11,
26
+ "r": 6,
27
+ "s": 8,
28
+ "t": 4,
29
+ "u": 12,
30
+ "v": 16,
31
+ "y": 17,
32
+ "|": 2
33
+ }