sanchit-gandhi HF staff commited on
Commit
abba8a0
1 Parent(s): fc7dc76

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": "mog",
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
+ "'": 13,
4
+ "-": 24,
5
+ "0": 32,
6
+ "1": 35,
7
+ "4": 33,
8
+ "a": 1,
9
+ "b": 10,
10
+ "c": 29,
11
+ "d": 11,
12
+ "e": 17,
13
+ "f": 34,
14
+ "g": 9,
15
+ "h": 20,
16
+ "i": 4,
17
+ "j": 27,
18
+ "k": 8,
19
+ "l": 18,
20
+ "m": 6,
21
+ "n": 2,
22
+ "o": 3,
23
+ "p": 14,
24
+ "r": 16,
25
+ "s": 12,
26
+ "t": 5,
27
+ "u": 7,
28
+ "w": 23,
29
+ "y": 15,
30
+ "z": 31,
31
+ "|": 0,
32
+ "á": 19,
33
+ "é": 30,
34
+ "í": 21,
35
+ "ó": 28,
36
+ "ú": 26,
37
+ "ḷ": 22,
38
+ "ḻ": 25
39
+ }