sanchit-gandhi HF staff commited on
Commit
963b8ed
1 Parent(s): 89e2e0f

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 +34 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "k",
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": "knf",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "normalize": true,
8
+ "pad_token": "k",
9
+ "phonemize": false,
10
+ "tokenizer_class": "VitsTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 26,
3
+ "'": 7,
4
+ "-": 24,
5
+ "_": 15,
6
+ "a": 20,
7
+ "b": 6,
8
+ "c": 29,
9
+ "d": 17,
10
+ "e": 3,
11
+ "f": 31,
12
+ "g": 21,
13
+ "h": 28,
14
+ "i": 8,
15
+ "j": 9,
16
+ "k": 0,
17
+ "l": 16,
18
+ "m": 19,
19
+ "n": 25,
20
+ "o": 11,
21
+ "p": 23,
22
+ "r": 30,
23
+ "t": 14,
24
+ "u": 5,
25
+ "w": 27,
26
+ "y": 10,
27
+ "ë": 1,
28
+ "ñ": 13,
29
+ "ŋ": 12,
30
+ "ş": 4,
31
+ "ţ": 22,
32
+ "ŧ": 18,
33
+ "–": 2
34
+ }