sanchit-gandhi HF staff commited on
Commit
07849af
1 Parent(s): 62bbcb9

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 +42 -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": "cuc",
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 39,
3
+ "1": 15,
4
+ "2": 7,
5
+ "3": 1,
6
+ "4": 4,
7
+ "5": 21,
8
+ "a": 3,
9
+ "b": 29,
10
+ "c": 13,
11
+ "d": 25,
12
+ "e": 8,
13
+ "f": 32,
14
+ "g": 20,
15
+ "h": 6,
16
+ "i": 2,
17
+ "j": 9,
18
+ "k": 38,
19
+ "l": 12,
20
+ "m": 17,
21
+ "n": 5,
22
+ "o": 10,
23
+ "p": 26,
24
+ "q": 19,
25
+ "r": 23,
26
+ "s": 16,
27
+ "t": 14,
28
+ "u": 11,
29
+ "v": 35,
30
+ "x": 37,
31
+ "y": 24,
32
+ "z": 36,
33
+ "|": 0,
34
+ "á": 31,
35
+ "é": 33,
36
+ "í": 30,
37
+ "ñ": 27,
38
+ "ó": 34,
39
+ "ú": 22,
40
+ "ŋ": 28,
41
+ "ˉ": 18
42
+ }