syllasgiorgos commited on
Commit
00521a0
1 Parent(s): 57387c3

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<unk>": 64
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "b",
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": "b",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "64": {
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": "ell",
24
+ "model_max_length": 1000000000000000019884624838656,
25
+ "normalize": true,
26
+ "pad_token": "b",
27
+ "phonemize": false,
28
+ "tokenizer_class": "VitsTokenizer",
29
+ "unk_token": "<unk>",
30
+ "verbose": false
31
+ }
vocab.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 24,
3
+ "'": 17,
4
+ "-": 13,
5
+ "0": 60,
6
+ "1": 1,
7
+ "2": 45,
8
+ "3": 47,
9
+ "4": 28,
10
+ "5": 4,
11
+ "6": 46,
12
+ "7": 12,
13
+ "8": 35,
14
+ "9": 32,
15
+ "_": 58,
16
+ "a": 27,
17
+ "b": 0,
18
+ "e": 48,
19
+ "h": 38,
20
+ "i": 7,
21
+ "k": 19,
22
+ "m": 43,
23
+ "n": 22,
24
+ "o": 44,
25
+ "p": 3,
26
+ "t": 23,
27
+ "x": 8,
28
+ "y": 25,
29
+ "z": 41,
30
+ "â": 30,
31
+ "ΐ": 63,
32
+ "ά": 10,
33
+ "έ": 52,
34
+ "ή": 2,
35
+ "ί": 6,
36
+ "α": 56,
37
+ "β": 29,
38
+ "γ": 33,
39
+ "δ": 9,
40
+ "ε": 37,
41
+ "ζ": 40,
42
+ "η": 42,
43
+ "θ": 5,
44
+ "ι": 54,
45
+ "κ": 31,
46
+ "λ": 11,
47
+ "μ": 55,
48
+ "ν": 39,
49
+ "ξ": 34,
50
+ "ο": 57,
51
+ "π": 15,
52
+ "ρ": 62,
53
+ "ς": 61,
54
+ "σ": 53,
55
+ "τ": 26,
56
+ "υ": 49,
57
+ "φ": 14,
58
+ "χ": 36,
59
+ "ψ": 21,
60
+ "ω": 16,
61
+ "ϊ": 18,
62
+ "ϋ": 51,
63
+ "ό": 20,
64
+ "ύ": 59,
65
+ "ώ": 50
66
+ }