sanchit-gandhi HF staff commited on
Commit
ad902f2
1 Parent(s): 53f0807

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": "e",
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": "cjo",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "e",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 27,
3
+ "'": 35,
4
+ "-": 33,
5
+ "0": 9,
6
+ "1": 1,
7
+ "2": 11,
8
+ "3": 3,
9
+ "4": 10,
10
+ "5": 19,
11
+ "6": 14,
12
+ "7": 34,
13
+ "8": 30,
14
+ "9": 26,
15
+ "_": 8,
16
+ "a": 22,
17
+ "c": 2,
18
+ "e": 0,
19
+ "g": 21,
20
+ "h": 7,
21
+ "i": 32,
22
+ "j": 15,
23
+ "k": 12,
24
+ "m": 20,
25
+ "n": 6,
26
+ "o": 4,
27
+ "p": 18,
28
+ "r": 28,
29
+ "s": 5,
30
+ "t": 29,
31
+ "u": 16,
32
+ "v": 23,
33
+ "w": 24,
34
+ "y": 31,
35
+ "z": 17,
36
+ "ñ": 25,
37
+ "—": 13
38
+ }