sanchit-gandhi HF staff commited on
Commit
f02ee4f
1 Parent(s): 4fbd77b

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": "|",
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": "sne",
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 39,
3
+ "'": 32,
4
+ "-": 20,
5
+ "0": 28,
6
+ "1": 31,
7
+ "2": 30,
8
+ "3": 35,
9
+ "4": 34,
10
+ "5": 38,
11
+ "6": 33,
12
+ "7": 36,
13
+ "a": 1,
14
+ "b": 17,
15
+ "c": 27,
16
+ "d": 6,
17
+ "e": 8,
18
+ "f": 23,
19
+ "g": 10,
20
+ "h": 9,
21
+ "i": 4,
22
+ "j": 19,
23
+ "k": 13,
24
+ "l": 21,
25
+ "m": 15,
26
+ "n": 2,
27
+ "o": 3,
28
+ "p": 16,
29
+ "q": 37,
30
+ "r": 14,
31
+ "s": 11,
32
+ "t": 12,
33
+ "u": 5,
34
+ "v": 26,
35
+ "w": 22,
36
+ "x": 29,
37
+ "y": 18,
38
+ "z": 25,
39
+ "|": 0,
40
+ "—": 24,
41
+ "ꞌ": 7
42
+ }