sanchit-gandhi HF staff commited on
Commit
1fe05e6
1 Parent(s): ed7882a

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