sanchit-gandhi HF staff commited on
Commit
a603f9a
1 Parent(s): 512d287

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