sanchit-gandhi HF staff commited on
Commit
afe744b
1 Parent(s): 8b58db2

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": "j",
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": "agu",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "j",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 13,
3
+ "'": 31,
4
+ "-": 26,
5
+ "6": 16,
6
+ "_": 37,
7
+ "a": 24,
8
+ "b": 3,
9
+ "c": 19,
10
+ "d": 14,
11
+ "e": 30,
12
+ "f": 12,
13
+ "g": 8,
14
+ "h": 20,
15
+ "i": 9,
16
+ "j": 0,
17
+ "k": 11,
18
+ "l": 39,
19
+ "m": 22,
20
+ "n": 29,
21
+ "o": 28,
22
+ "p": 23,
23
+ "q": 38,
24
+ "r": 1,
25
+ "s": 5,
26
+ "t": 6,
27
+ "u": 21,
28
+ "v": 7,
29
+ "w": 27,
30
+ "x": 10,
31
+ "y": 17,
32
+ "z": 18,
33
+ "á": 36,
34
+ "é": 4,
35
+ "í": 35,
36
+ "ñ": 33,
37
+ "ó": 2,
38
+ "ú": 34,
39
+ "ẍ": 25,
40
+ "—": 15,
41
+ "ꞌ": 32
42
+ }