cheelam commited on
Commit
f526ac9
1 Parent(s): fb922df

Upload tokenizer

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