khof312 commited on
Commit
aec187c
1 Parent(s): cab437e

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 39
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "2",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "unk_token": {
10
+ "content": "<unk>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_blank": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "2",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "39": {
13
+ "content": "<unk>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "clean_up_tokenization_spaces": true,
22
+ "is_uroman": false,
23
+ "language": "swh",
24
+ "model_max_length": 1000000000000000019884624838656,
25
+ "normalize": true,
26
+ "pad_token": "2",
27
+ "phonemize": false,
28
+ "tokenizer_class": "VitsTokenizer",
29
+ "unk_token": "<unk>",
30
+ "verbose": false
31
+ }
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
+ }