sanchit-gandhi HF staff commited on
Commit
40b3bdc
1 Parent(s): 230e751

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 +45 -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": "hak",
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 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 42,
3
+ "'": 41,
4
+ "-": 2,
5
+ "`": 37,
6
+ "a": 14,
7
+ "c": 10,
8
+ "e": 9,
9
+ "f": 29,
10
+ "g": 6,
11
+ "h": 3,
12
+ "i": 4,
13
+ "k": 5,
14
+ "l": 16,
15
+ "m": 17,
16
+ "n": 1,
17
+ "o": 12,
18
+ "p": 19,
19
+ "s": 11,
20
+ "t": 7,
21
+ "u": 8,
22
+ "v": 30,
23
+ "y": 15,
24
+ "|": 0,
25
+ "à": 25,
26
+ "á": 28,
27
+ "â": 18,
28
+ "è": 34,
29
+ "é": 35,
30
+ "ê": 20,
31
+ "ì": 13,
32
+ "í": 36,
33
+ "î": 24,
34
+ "ò": 26,
35
+ "ó": 21,
36
+ "ô": 31,
37
+ "ù": 33,
38
+ "ú": 32,
39
+ "û": 23,
40
+ "̀": 39,
41
+ "́": 38,
42
+ "̂": 40,
43
+ "̍": 27,
44
+ "ṳ": 22
45
+ }