sanchit-gandhi HF staff commited on
Commit
3d2269b
1 Parent(s): 034c522

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 +49 -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": "sri",
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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 46,
3
+ "'": 40,
4
+ "a": 2,
5
+ "b": 16,
6
+ "c": 32,
7
+ "d": 17,
8
+ "e": 4,
9
+ "f": 37,
10
+ "g": 9,
11
+ "h": 36,
12
+ "i": 5,
13
+ "j": 20,
14
+ "k": 14,
15
+ "l": 33,
16
+ "m": 7,
17
+ "n": 24,
18
+ "o": 11,
19
+ "p": 13,
20
+ "q": 44,
21
+ "r": 1,
22
+ "s": 10,
23
+ "t": 22,
24
+ "u": 12,
25
+ "v": 38,
26
+ "w": 23,
27
+ "x": 45,
28
+ "y": 18,
29
+ "z": 43,
30
+ "|": 0,
31
+ "á": 29,
32
+ "ã": 3,
33
+ "é": 30,
34
+ "í": 27,
35
+ "ñ": 26,
36
+ "ó": 35,
37
+ "õ": 21,
38
+ "ú": 31,
39
+ "ü": 39,
40
+ "ĩ": 8,
41
+ "ũ": 25,
42
+ "ʉ": 6,
43
+ "́": 28,
44
+ "̃": 15,
45
+ "̶": 42,
46
+ "ṍ": 41,
47
+ "ẽ": 19,
48
+ "—": 34
49
+ }