sanchit-gandhi HF staff commited on
Commit
62b1366
1 Parent(s): 99f48de

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": "ꞌ",
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": "ncl",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "ꞌ",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 25,
3
+ "0": 10,
4
+ "2": 28,
5
+ "_": 11,
6
+ "a": 17,
7
+ "b": 21,
8
+ "c": 16,
9
+ "d": 14,
10
+ "e": 19,
11
+ "f": 8,
12
+ "g": 7,
13
+ "h": 1,
14
+ "i": 34,
15
+ "j": 31,
16
+ "k": 24,
17
+ "l": 2,
18
+ "m": 6,
19
+ "n": 4,
20
+ "o": 5,
21
+ "p": 26,
22
+ "q": 22,
23
+ "r": 23,
24
+ "s": 29,
25
+ "t": 33,
26
+ "u": 27,
27
+ "v": 3,
28
+ "x": 18,
29
+ "y": 13,
30
+ "z": 9,
31
+ "á": 20,
32
+ "é": 15,
33
+ "í": 32,
34
+ "ñ": 36,
35
+ "ó": 30,
36
+ "ú": 12,
37
+ "—": 35,
38
+ "ꞌ": 0
39
+ }