sanchit-gandhi HF staff commited on
Commit
4775871
1 Parent(s): 2a52cda

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