Commit
·
ccda601
1
Parent(s):
5ee3afd
Upload tokenizer
Browse files- special_tokens_map.json +4 -0
- tokenizer_config.json +12 -0
- vocab.json +54 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pad_token": "î",
|
| 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": "btt",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"normalize": true,
|
| 8 |
+
"pad_token": "î",
|
| 9 |
+
"phonemize": false,
|
| 10 |
+
"tokenizer_class": "VitsTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
" ": 4,
|
| 3 |
+
"'": 37,
|
| 4 |
+
"-": 16,
|
| 5 |
+
"_": 24,
|
| 6 |
+
"a": 9,
|
| 7 |
+
"b": 40,
|
| 8 |
+
"c": 38,
|
| 9 |
+
"d": 34,
|
| 10 |
+
"e": 51,
|
| 11 |
+
"f": 27,
|
| 12 |
+
"g": 12,
|
| 13 |
+
"h": 50,
|
| 14 |
+
"i": 2,
|
| 15 |
+
"j": 22,
|
| 16 |
+
"k": 3,
|
| 17 |
+
"l": 25,
|
| 18 |
+
"m": 30,
|
| 19 |
+
"n": 21,
|
| 20 |
+
"o": 45,
|
| 21 |
+
"p": 8,
|
| 22 |
+
"r": 29,
|
| 23 |
+
"s": 7,
|
| 24 |
+
"t": 20,
|
| 25 |
+
"u": 44,
|
| 26 |
+
"w": 14,
|
| 27 |
+
"y": 35,
|
| 28 |
+
"z": 33,
|
| 29 |
+
"à": 47,
|
| 30 |
+
"á": 15,
|
| 31 |
+
"â": 31,
|
| 32 |
+
"è": 26,
|
| 33 |
+
"é": 23,
|
| 34 |
+
"ê": 18,
|
| 35 |
+
"ì": 46,
|
| 36 |
+
"í": 11,
|
| 37 |
+
"î": 0,
|
| 38 |
+
"ò": 41,
|
| 39 |
+
"ó": 5,
|
| 40 |
+
"ù": 19,
|
| 41 |
+
"ú": 48,
|
| 42 |
+
"û": 13,
|
| 43 |
+
"ā": 28,
|
| 44 |
+
"ē": 6,
|
| 45 |
+
"ě": 17,
|
| 46 |
+
"ī": 36,
|
| 47 |
+
"ı": 43,
|
| 48 |
+
"ō": 49,
|
| 49 |
+
"ū": 10,
|
| 50 |
+
"ǎ": 1,
|
| 51 |
+
"ǐ": 42,
|
| 52 |
+
"ǒ": 32,
|
| 53 |
+
"ǔ": 39
|
| 54 |
+
}
|