sanchit-gandhi commited on
Commit
3439e64
·
1 Parent(s): b55fa0e

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