sanchit-gandhi HF staff commited on
Commit
7331742
1 Parent(s): 9dd968c

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 +39 -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": "cou",
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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 36,
3
+ "'": 32,
4
+ "-": 33,
5
+ "a": 1,
6
+ "b": 29,
7
+ "c": 25,
8
+ "d": 21,
9
+ "e": 7,
10
+ "f": 18,
11
+ "g": 23,
12
+ "h": 4,
13
+ "i": 5,
14
+ "j": 28,
15
+ "k": 6,
16
+ "l": 13,
17
+ "m": 16,
18
+ "n": 3,
19
+ "o": 9,
20
+ "p": 24,
21
+ "r": 12,
22
+ "s": 17,
23
+ "t": 11,
24
+ "u": 10,
25
+ "v": 14,
26
+ "w": 8,
27
+ "y": 15,
28
+ "|": 0,
29
+ "á": 34,
30
+ "ë": 2,
31
+ "ñ": 31,
32
+ "ŋ": 22,
33
+ "ƴ": 30,
34
+ "ɓ": 27,
35
+ "ɗ": 19,
36
+ "̃": 20,
37
+ "ỹ": 26,
38
+ "—": 35
39
+ }