{ "added_tokens_decoder": { "1": { "content": "(cmn)", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "2": { "content": "(de)", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "3": { "content": "(en)", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "4": { "content": "(es)", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "5": { "content": "(fr)", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "6": { "content": "(it)", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "7": { "content": "(ko)", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "9": { "content": "??", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "11": { "content": "a1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "12": { "content": "a2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "13": { "content": "a5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "14": { "content": "ai1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "15": { "content": "ai2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "16": { "content": "ai5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "17": { "content": "aiɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "18": { "content": "aɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "19": { "content": "aɪ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "20": { "content": "aɪə", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "21": { "content": "aɪɚ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "22": { "content": "aʊ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "23": { "content": "aː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "25": { "content": "bː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "27": { "content": "dz", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "28": { "content": "dzː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "29": { "content": "dʑ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "30": { "content": "dʒ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "31": { "content": "dʒː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "32": { "content": "dː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "33": { "content": "d̪", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "35": { "content": "ei1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "36": { "content": "ei2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "37": { "content": "ei5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "38": { "content": "eiɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "39": { "content": "eə", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "40": { "content": "eɪ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "41": { "content": "eʊ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "42": { "content": "eː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "45": { "content": "hʲ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "47": { "content": "i.1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "48": { "content": "i.2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "49": { "content": "i.5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "50": { "content": "i.ɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "51": { "content": "i1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "52": { "content": "i2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "53": { "content": "i5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "54": { "content": "iou1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "55": { "content": "iou2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "56": { "content": "iou5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "57": { "content": "iouɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "58": { "content": "iɑ1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "59": { "content": "iɑ2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "60": { "content": "iɑ5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "61": { "content": "iɑɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "62": { "content": "iə", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "63": { "content": "iɛ1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "64": { "content": "iɛ2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "65": { "content": "iɛ5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "66": { "content": "iɛɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "67": { "content": "iɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "68": { "content": "iː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "69": { "content": "i̪1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "70": { "content": "i̪2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "71": { "content": "i̪5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "72": { "content": "i̪ɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "75": { "content": "kh", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "76": { "content": "kː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "80": { "content": "n̩", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "82": { "content": "o1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "83": { "content": "o2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "84": { "content": "o5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "85": { "content": "onɡ1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "86": { "content": "onɡ2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "87": { "content": "onɡ5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "88": { "content": "onɡɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "89": { "content": "ou1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "90": { "content": "ou2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "91": { "content": "ou5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "92": { "content": "ouɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "93": { "content": "oɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "94": { "content": "oɪ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "95": { "content": "oʊ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "96": { "content": "oː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "97": { "content": "oːɹ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "99": { "content": "pf", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "100": { "content": "ph", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "101": { "content": "pː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "105": { "content": "s.", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "106": { "content": "ss", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "108": { "content": "th", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "109": { "content": "ts", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "110": { "content": "ts.", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "111": { "content": "ts.h", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "112": { "content": "tsh", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "113": { "content": "tsː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "114": { "content": "tɕ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "115": { "content": "tɕh", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "116": { "content": "tʃ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "117": { "content": "tʃː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "118": { "content": "tː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "119": { "content": "t̪", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "121": { "content": "u1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "122": { "content": "u2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "123": { "content": "u5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "124": { "content": "ua1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "125": { "content": "ua2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "126": { "content": "ua5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "127": { "content": "uai2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "128": { "content": "uai5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "129": { "content": "uaiɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "130": { "content": "uaɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "131": { "content": "uei1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "132": { "content": "uei2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "133": { "content": "uei5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "134": { "content": "ueiɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "135": { "content": "uo1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "136": { "content": "uo2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "137": { "content": "uo5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "138": { "content": "uoɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "139": { "content": "uə1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "140": { "content": "uə2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "141": { "content": "uə5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "142": { "content": "uəɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "143": { "content": "uɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "144": { "content": "uɪ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "145": { "content": "uː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "150": { "content": "y1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "151": { "content": "y2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "152": { "content": "y5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "153": { "content": "yiɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "154": { "content": "yæ1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "155": { "content": "yæ2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "156": { "content": "yæ5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "157": { "content": "yæɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "158": { "content": "yə2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "159": { "content": "yə5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "160": { "content": "yəɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "161": { "content": "yɛ1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "162": { "content": "yɛ2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "163": { "content": "yɛ5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "164": { "content": "yɛɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "165": { "content": "yɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "166": { "content": "yː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "172": { "content": "øː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "175": { "content": "œ̃", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "178": { "content": "ɑ1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "179": { "content": "ɑ2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "180": { "content": "ɑ5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "181": { "content": "ɑu1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "182": { "content": "ɑu2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "183": { "content": "ɑu5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "184": { "content": "ɑuɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "185": { "content": "ɑɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "186": { "content": "ɑː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "187": { "content": "ɑːɹ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "188": { "content": "ɑ̃", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "191": { "content": "ɔø", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "192": { "content": "ɔɪ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "193": { "content": "ɔː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "194": { "content": "ɔːɹ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "195": { "content": "ɔ̃", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "198": { "content": "ə1", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "199": { "content": "ə2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "200": { "content": "ə5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "201": { "content": "əl", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "202": { "content": "ər2", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "203": { "content": "ər5", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "204": { "content": "ərɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "205": { "content": "əɜ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "206": { "content": "əʊ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "207": { "content": "əː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "210": { "content": "ɛɪ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "211": { "content": "ɛɹ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "212": { "content": "ɛː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "213": { "content": "ɛ̃", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "215": { "content": "ɜː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "218": { "content": "ɡː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "221": { "content": "ɪɹ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "222": { "content": "ɪː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "232": { "content": "ʊə", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "233": { "content": "ʊɹ", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "234": { "content": "ʊː", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "245": { "content": "[UNK]", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "246": { "content": "[PAD]", "lstrip": true, "normalized": false, "rstrip": true, "single_word": false, "special": false }, "247": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "248": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true } }, "bos_token": "", "clean_up_tokenization_spaces": true, "do_lower_case": false, "eos_token": "", "model_max_length": 1000000000000000019884624838656, "pad_token": "[PAD]", "processor_class": "Wav2Vec2Processor", "replace_word_delimiter_char": " ", "target_lang": null, "tokenizer_class": "Wav2Vec2CTCTokenizer", "unk_token": "[UNK]", "word_delimiter_token": "|" }