sanchit-gandhi HF staff commited on
Commit
cb53794
1 Parent(s): 99f48de

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