manga-ocr / tokenizer_config.json
Maciej Budyś
manga-ocr-base
0808c80
raw
history blame
486 Bytes
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "do_lower_case": false, "do_word_tokenize": true, "do_subword_tokenize": true, "word_tokenizer_type": "mecab", "subword_tokenizer_type": "character", "never_split": null, "mecab_kwargs": {"mecab_dic": "unidic_lite"}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "cl-tohoku/bert-base-japanese-char-v2", "tokenizer_class": "BertJapaneseTokenizer"}