Commit
•
0da3fb2
1
Parent(s):
a7237ec
Upload tokenizer
Browse files- special_tokens_map.json +4 -0
- tokenizer_config.json +12 -0
- vocab.json +42 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "a",
|
3 |
+
"unk_token": "<unk>"
|
4 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_blank": true,
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"is_uroman": false,
|
5 |
+
"language": "agn",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"normalize": true,
|
8 |
+
"pad_token": "a",
|
9 |
+
"phonemize": false,
|
10 |
+
"tokenizer_class": "VitsTokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
" ": 39,
|
3 |
+
"'": 27,
|
4 |
+
"-": 18,
|
5 |
+
"0": 30,
|
6 |
+
"1": 32,
|
7 |
+
"2": 37,
|
8 |
+
"5": 36,
|
9 |
+
"6": 34,
|
10 |
+
"7": 38,
|
11 |
+
"a": 0,
|
12 |
+
"b": 15,
|
13 |
+
"c": 21,
|
14 |
+
"d": 8,
|
15 |
+
"e": 11,
|
16 |
+
"f": 23,
|
17 |
+
"g": 3,
|
18 |
+
"h": 22,
|
19 |
+
"i": 4,
|
20 |
+
"j": 20,
|
21 |
+
"k": 14,
|
22 |
+
"l": 10,
|
23 |
+
"m": 7,
|
24 |
+
"n": 2,
|
25 |
+
"o": 5,
|
26 |
+
"p": 12,
|
27 |
+
"q": 26,
|
28 |
+
"r": 13,
|
29 |
+
"s": 9,
|
30 |
+
"t": 6,
|
31 |
+
"u": 19,
|
32 |
+
"v": 25,
|
33 |
+
"w": 17,
|
34 |
+
"x": 31,
|
35 |
+
"y": 16,
|
36 |
+
"z": 24,
|
37 |
+
"|": 1,
|
38 |
+
"ā": 28,
|
39 |
+
"ē": 35,
|
40 |
+
"ō": 29,
|
41 |
+
"—": 33
|
42 |
+
}
|