sanchit-gandhi HF staff commited on
Commit
6e336a0
1 Parent(s): 4152d7a

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