{ "added_tokens_decoder": { "0": { "content": "[UNK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "[PAD]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "[CLS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "3": { "content": "[SEP]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "4": { "content": "[MASK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "5": { "content": "[p]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "6": { "content": "[t]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "7": { "content": "[k]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "8": { "content": "[kp]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "9": { "content": "[b]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "10": { "content": "[d]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "11": { "content": "[g]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "12": { "content": "[gb]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "13": { "content": "[ɓ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "14": { "content": "[ɗ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "15": { "content": "[ƴ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "16": { "content": "[pf]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "17": { "content": "[tf]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "18": { "content": "[ts]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "19": { "content": "[c]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "20": { "content": "[kf]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "21": { "content": "[bv]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "22": { "content": "[dv]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "23": { "content": "[dz]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "24": { "content": "[j]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "25": { "content": "[gv]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "26": { "content": "[f]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "27": { "content": "[s]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "28": { "content": "[sh]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "29": { "content": "[x]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "30": { "content": "[xf]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "31": { "content": "[h]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "32": { "content": "[v]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "33": { "content": "[z]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "34": { "content": "[zh]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "35": { "content": "[gh]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "36": { "content": "[hv]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "37": { "content": "[m]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "38": { "content": "[n]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "39": { "content": "[ny]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "40": { "content": "[ŋ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "41": { "content": "[ŋm]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "42": { "content": "[l]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "43": { "content": "[sl]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "44": { "content": "[zl]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "45": { "content": "[ʙ**]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "46": { "content": "[vb]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "47": { "content": "[r]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "48": { "content": "[ẅ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "49": { "content": "[y]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "50": { "content": "[w]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "51": { "content": "[i]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "52": { "content": "[ɨ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "53": { "content": "[ʉ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "54": { "content": "[u]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "55": { "content": "[e]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "56": { "content": "[ø]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "57": { "content": "[ɤ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "58": { "content": "[o]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "59": { "content": "[ɛ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "60": { "content": "[œ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "61": { "content": "[ə]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "62": { "content": "[ɔ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "63": { "content": "[æ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "64": { "content": "[a]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "65": { "content": "[ɑ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "66": { "content": "[α]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "67": { "content": "[áà]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "68": { "content": "[àá]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "69": { "content": "[áa]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "70": { "content": "[aá]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "71": { "content": "[áá]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "72": { "content": "[əə́]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "73": { "content": "[ɛ́ɛ]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "74": { "content": "[ɛ́ɛ́]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "75": { "content": "[ə́ə́]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "76": { "content": "[ú]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "77": { "content": "[ó]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "78": { "content": "[ɔ́]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "79": { "content": "[ɔ́ɔ́]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "80": { "content": "[á]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "81": { "content": "[ə́]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "82": { "content": "[ɔɔ́]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "83": { "content": "[óó]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "84": { "content": "[í]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "85": { "content": "[Ɛ́]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "86": { "content": "[...]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "87": { "content": "[-]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "88": { "content": "[—]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "89": { "content": "[–]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "90": { "content": "[_]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "91": { "content": "[°]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "92": { "content": "[«]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "93": { "content": "[»]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "94": { "content": "[(]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "95": { "content": "[)]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "96": { "content": "[[]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "97": { "content": "[]]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "98": { "content": "[{]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "99": { "content": "[}]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "100": { "content": "[<]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "101": { "content": "[>]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "102": { "content": "[&]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "103": { "content": "[*]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "104": { "content": "[#]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "105": { "content": "[$]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "106": { "content": "[£]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "107": { "content": "[%]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "108": { "content": "[+]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "109": { "content": "[=]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "110": { "content": "[|]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "111": { "content": "[/]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "112": { "content": "[\\]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "113": { "content": "[@]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "114": { "content": "[www]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "do_lower_case": true, "mask_token": "[MASK]", "model_max_length": 1000000000000000019884624838656, "pad_token": "[PAD]", "sep_token": "[SEP]", "strip_accents": null, "tokenize_chinese_chars": true, "tokenizer_class": "BertTokenizer", "unk_token": "[UNK]" }