Upload tokenizer
Browse files- special_tokens_map.json +4 -0
- tokenizer_config.json +9 -0
- vocab.json +48 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "<pad>",
|
3 |
+
"unk_token": "<unk>"
|
4 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_blank": true,
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"language": null,
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"tokenizer_class": "VitsMmsTokenizer",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
" ": 29,
|
3 |
+
"'": 41,
|
4 |
+
"-": 2,
|
5 |
+
"<pad>": 44,
|
6 |
+
"<unk>": 45,
|
7 |
+
"_": 14,
|
8 |
+
"a": 19,
|
9 |
+
"b": 18,
|
10 |
+
"c": 10,
|
11 |
+
"d": 17,
|
12 |
+
"e": 15,
|
13 |
+
"f": 20,
|
14 |
+
"g": 11,
|
15 |
+
"h": 22,
|
16 |
+
"i": 16,
|
17 |
+
"j": 36,
|
18 |
+
"k": 25,
|
19 |
+
"l": 43,
|
20 |
+
"m": 42,
|
21 |
+
"n": 34,
|
22 |
+
"o": 35,
|
23 |
+
"p": 31,
|
24 |
+
"q": 9,
|
25 |
+
"r": 23,
|
26 |
+
"s": 26,
|
27 |
+
"t": 33,
|
28 |
+
"u": 4,
|
29 |
+
"v": 27,
|
30 |
+
"x": 8,
|
31 |
+
"y": 6,
|
32 |
+
"z": 1,
|
33 |
+
"à": 28,
|
34 |
+
"â": 38,
|
35 |
+
"ç": 39,
|
36 |
+
"è": 7,
|
37 |
+
"é": 24,
|
38 |
+
"ê": 13,
|
39 |
+
"ë": 32,
|
40 |
+
"î": 0,
|
41 |
+
"ï": 40,
|
42 |
+
"ô": 12,
|
43 |
+
"ù": 3,
|
44 |
+
"û": 5,
|
45 |
+
"ü": 37,
|
46 |
+
"œ": 21,
|
47 |
+
"–": 30
|
48 |
+
}
|