bert-base-japanese-minutes-further / tokenizer_config.json

Upload 4 files

bc605e2 about 1 year ago

188 Bytes

	{
	"do_lower_case": false,
	"word_tokenizer_type": "mecab",
	"subword_tokenizer_type": "wordpiece",
	"mecab_kwargs": {
	"normalize_text": true,
	"mecab_dic": "unidic_lite"
	}
	}