sanchit-gandhi HF staff commited on
Commit
29a84d1
1 Parent(s): 8fb389d

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 +38 -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": "hay",
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 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 35,
3
+ "'": 18,
4
+ "0": 26,
5
+ "1": 27,
6
+ "2": 28,
7
+ "3": 30,
8
+ "4": 29,
9
+ "5": 31,
10
+ "6": 33,
11
+ "7": 34,
12
+ "8": 32,
13
+ "a": 0,
14
+ "b": 7,
15
+ "c": 24,
16
+ "d": 20,
17
+ "e": 6,
18
+ "f": 22,
19
+ "g": 11,
20
+ "h": 15,
21
+ "i": 2,
22
+ "j": 21,
23
+ "k": 8,
24
+ "l": 16,
25
+ "m": 9,
26
+ "n": 4,
27
+ "o": 5,
28
+ "p": 23,
29
+ "r": 10,
30
+ "s": 17,
31
+ "t": 13,
32
+ "u": 3,
33
+ "v": 25,
34
+ "w": 12,
35
+ "y": 14,
36
+ "z": 19,
37
+ "|": 1
38
+ }