sanchit-gandhi HF staff commited on
Commit
2c772af
1 Parent(s): 1cc4d7e

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 +47 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "y",
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": "pjt",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "y",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 35,
3
+ "'": 13,
4
+ "-": 30,
5
+ "0": 37,
6
+ "1": 28,
7
+ "2": 36,
8
+ "3": 14,
9
+ "4": 8,
10
+ "5": 18,
11
+ "6": 6,
12
+ "7": 41,
13
+ "8": 22,
14
+ "9": 17,
15
+ "_": 11,
16
+ "a": 44,
17
+ "b": 10,
18
+ "c": 4,
19
+ "d": 1,
20
+ "e": 38,
21
+ "f": 32,
22
+ "g": 26,
23
+ "h": 23,
24
+ "i": 42,
25
+ "j": 39,
26
+ "k": 43,
27
+ "l": 24,
28
+ "m": 2,
29
+ "n": 31,
30
+ "o": 25,
31
+ "p": 12,
32
+ "r": 34,
33
+ "s": 20,
34
+ "t": 40,
35
+ "u": 29,
36
+ "v": 3,
37
+ "w": 21,
38
+ "x": 27,
39
+ "y": 0,
40
+ "z": 5,
41
+ "ḻ": 7,
42
+ "ṉ": 16,
43
+ "ṟ": 15,
44
+ "ṯ": 33,
45
+ "–": 19,
46
+ "—": 9
47
+ }