sanchit-gandhi HF staff commited on
Commit
1809770
1 Parent(s): 9a7beb9

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 +46 -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": "mop",
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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 43,
3
+ "'": 2,
4
+ "-": 27,
5
+ "0": 31,
6
+ "1": 34,
7
+ "2": 33,
8
+ "3": 37,
9
+ "4": 40,
10
+ "5": 38,
11
+ "6": 39,
12
+ "7": 42,
13
+ "9": 41,
14
+ "a": 1,
15
+ "b": 12,
16
+ "c": 6,
17
+ "d": 21,
18
+ "e": 5,
19
+ "f": 28,
20
+ "g": 26,
21
+ "h": 16,
22
+ "i": 3,
23
+ "j": 11,
24
+ "k": 35,
25
+ "l": 9,
26
+ "m": 14,
27
+ "n": 10,
28
+ "o": 8,
29
+ "p": 19,
30
+ "q": 18,
31
+ "r": 24,
32
+ "s": 13,
33
+ "t": 7,
34
+ "u": 4,
35
+ "v": 29,
36
+ "w": 20,
37
+ "x": 17,
38
+ "y": 15,
39
+ "z": 23,
40
+ "|": 0,
41
+ "é": 30,
42
+ "ñ": 36,
43
+ "ü": 22,
44
+ "у": 32,
45
+ "—": 25
46
+ }