Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +4 -0
- tokenizer_config.json +31 -0
- vocab.json +28 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<unk>": 26
|
3 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "b",
|
3 |
+
"unk_token": "<unk>"
|
4 |
+
}
|
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 |
+
"26": {
|
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": "eus",
|
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 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
" ": 3,
|
3 |
+
"-": 25,
|
4 |
+
"_": 7,
|
5 |
+
"a": 11,
|
6 |
+
"b": 0,
|
7 |
+
"d": 22,
|
8 |
+
"e": 16,
|
9 |
+
"f": 8,
|
10 |
+
"g": 15,
|
11 |
+
"h": 12,
|
12 |
+
"i": 23,
|
13 |
+
"j": 20,
|
14 |
+
"k": 19,
|
15 |
+
"l": 14,
|
16 |
+
"m": 17,
|
17 |
+
"n": 21,
|
18 |
+
"o": 2,
|
19 |
+
"p": 6,
|
20 |
+
"r": 9,
|
21 |
+
"s": 4,
|
22 |
+
"t": 13,
|
23 |
+
"u": 5,
|
24 |
+
"v": 18,
|
25 |
+
"x": 10,
|
26 |
+
"z": 24,
|
27 |
+
"—": 1
|
28 |
+
}
|