sanchit-gandhi HF staff commited on
Commit
2247783
1 Parent(s): f08052f

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