sanchit-gandhi HF staff commited on
Commit
794fe52
1 Parent(s): 1897d7f

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