w2v-bert-2.0 / tokenizer_config.json
AlexHung29629's picture
Upload tokenizer
425e05c verified
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"1": {
"content": "<s>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"2": {
"content": "</s>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"3": {
"content": "<unk>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"30": {
"content": "iː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"37": {
"content": "aɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"41": {
"content": "ɑː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"44": {
"content": "eɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"46": {
"content": "uː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"48": {
"content": "ɑ̃",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"49": {
"content": "oʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"51": {
"content": "eː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"53": {
"content": "aʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"54": {
"content": "ts",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"55": {
"content": "oː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"56": {
"content": "ɔ̃",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"60": {
"content": "dʒ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"61": {
"content": "əl",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"63": {
"content": "ɜː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"66": {
"content": "tʃ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"67": {
"content": "ɔː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"68": {
"content": "ɑːɹ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"69": {
"content": "ɛ̃",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"71": {
"content": "ɔːɹ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"73": {
"content": "aː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"77": {
"content": "oːɹ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"79": {
"content": "yː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"81": {
"content": "iə",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"82": {
"content": "i5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"83": {
"content": "s.",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"84": {
"content": "tɕ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"85": {
"content": "??",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"86": {
"content": "nʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"87": {
"content": "ɛː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"88": {
"content": "œ̃",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"90": {
"content": "ɔø",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"92": {
"content": "tʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"94": {
"content": "ɛɹ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"95": {
"content": "ts.",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"96": {
"content": "rʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"97": {
"content": "ɪɹ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"98": {
"content": "ɭʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"99": {
"content": "i.5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"100": {
"content": "ɔɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"102": {
"content": "sʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"103": {
"content": "u5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"104": {
"content": "ʊɹ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"105": {
"content": "iɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"106": {
"content": "a5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"107": {
"content": "iɛ5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"108": {
"content": "øː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"110": {
"content": "ja",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"111": {
"content": "əɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"112": {
"content": "th",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"113": {
"content": "ɑ5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"114": {
"content": "oɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"115": {
"content": "dʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"116": {
"content": "ə5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"117": {
"content": "tɕh",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"118": {
"content": "ts.h",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"119": {
"content": "mʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"121": {
"content": "dʑ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"122": {
"content": "vʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"123": {
"content": "e̞",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"124": {
"content": "tʃʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"125": {
"content": "ei5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"126": {
"content": "o5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"127": {
"content": "onɡ5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"128": {
"content": "ɑu5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"129": {
"content": "iɑ5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"130": {
"content": "ai5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"131": {
"content": "aɪɚ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"132": {
"content": "kh",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"133": {
"content": "ə1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"135": {
"content": "i2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"138": {
"content": "t[",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"139": {
"content": "aɪə",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"141": {
"content": "ju",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"142": {
"content": "ə2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"143": {
"content": "u2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"144": {
"content": "oɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"145": {
"content": "pː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"146": {
"content": "iɛɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"147": {
"content": "ou5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"148": {
"content": "y5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"149": {
"content": "uɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"150": {
"content": "tː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"151": {
"content": "uo5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"152": {
"content": "d[",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"153": {
"content": "uoɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"154": {
"content": "tsh",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"155": {
"content": "ɑɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"157": {
"content": "i̪5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"158": {
"content": "uei5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"160": {
"content": "aɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"161": {
"content": "ɑɨ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"162": {
"content": "i.ɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"163": {
"content": "eʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"164": {
"content": "o2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"165": {
"content": "ɐ̃",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"167": {
"content": "pʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"168": {
"content": "kʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"169": {
"content": "n̩",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"171": {
"content": "ph",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"172": {
"content": "ɑu2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"173": {
"content": "uɨ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"174": {
"content": "əɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"177": {
"content": "yɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"178": {
"content": "bʲ",
"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": "s̪",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"181": {
"content": "aiɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"183": {
"content": "ɐ̃ʊ̃",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"185": {
"content": "ə4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"186": {
"content": "yæɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"187": {
"content": "a2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"188": {
"content": "ɨː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"189": {
"content": "t̪",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"190": {
"content": "iouɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"191": {
"content": "ũ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"192": {
"content": "onɡɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"193": {
"content": "aɨ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"194": {
"content": "iɛ2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"195": {
"content": "ɔɨ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"196": {
"content": "ɑuɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"197": {
"content": "o̞",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"198": {
"content": "ei2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"199": {
"content": "iou2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"201": {
"content": "kː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"202": {
"content": "y2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"204": {
"content": "oe",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"205": {
"content": "dˤ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"206": {
"content": "yɛɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"207": {
"content": "əʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"209": {
"content": "ɡʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"210": {
"content": "onɡ2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"211": {
"content": "u\"",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"212": {
"content": "eiɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"214": {
"content": "ɯᵝ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"215": {
"content": "iou5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"216": {
"content": "dZ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"217": {
"content": "r̝̊",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"218": {
"content": "i.2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"219": {
"content": "tS",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"220": {
"content": "s^",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"222": {
"content": "yə5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"223": {
"content": "iɑɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"224": {
"content": "uə5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"225": {
"content": "pf",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"226": {
"content": "ɨu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"227": {
"content": "iɑ2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"228": {
"content": "ou2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"229": {
"content": "ər2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"230": {
"content": "fʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"231": {
"content": "ai2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"232": {
"content": "r̝",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"233": {
"content": "uəɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"235": {
"content": "əɨ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"236": {
"content": "ua5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"237": {
"content": "uɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"239": {
"content": "bː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"240": {
"content": "yu5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"241": {
"content": "uo2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"242": {
"content": "yɛ5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"243": {
"content": "l̩",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"245": {
"content": "ərɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"247": {
"content": "i̪2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"248": {
"content": "ouɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"249": {
"content": "uaɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"250": {
"content": "a.",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"251": {
"content": "a.ː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"252": {
"content": "yæ5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"253": {
"content": "dː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"254": {
"content": "r̩",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"255": {
"content": "ee",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"256": {
"content": "ɪu",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"257": {
"content": "ər5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"258": {
"content": "i̪ɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"259": {
"content": "æi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"260": {
"content": "u:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"261": {
"content": "i.ː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"262": {
"content": "t^",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"263": {
"content": "o1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"264": {
"content": "ɪ^",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"265": {
"content": "ai",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"266": {
"content": "ueiɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"267": {
"content": "æː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"268": {
"content": "ɛɪ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"269": {
"content": "eə",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"270": {
"content": "i.",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"272": {
"content": "ie",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"273": {
"content": "ua2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"274": {
"content": "ɑ1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"275": {
"content": "o4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"276": {
"content": "tʃː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"277": {
"content": "o:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"278": {
"content": "ɑ:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"279": {
"content": "u1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"281": {
"content": "i̪1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"282": {
"content": "au",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"283": {
"content": "yæ2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"284": {
"content": "u.",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"285": {
"content": "qː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"286": {
"content": "yəɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"287": {
"content": "y:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"288": {
"content": "kʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"289": {
"content": "tʃʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"290": {
"content": "iʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"291": {
"content": "sx",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"292": {
"content": "õ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"293": {
"content": "uo",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"294": {
"content": "tʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"295": {
"content": "uai5",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"296": {
"content": "bʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"297": {
"content": "u.ː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"298": {
"content": "uə2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"299": {
"content": "ʊə",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"300": {
"content": "d^",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"301": {
"content": "s̪ː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"302": {
"content": "yiɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"303": {
"content": "dʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"304": {
"content": "r.",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"305": {
"content": "oe:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"306": {
"content": "i1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"307": {
"content": "ɟː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"308": {
"content": "yu2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"309": {
"content": "nʲʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"310": {
"content": "i̪4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"311": {
"content": "uei2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"312": {
"content": "tsʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"314": {
"content": "ĩ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"315": {
"content": "ɑ4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"316": {
"content": "t̪ː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"317": {
"content": "eɑ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"318": {
"content": "u4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"319": {
"content": "e:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"320": {
"content": "tsː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"321": {
"content": "ʈʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"322": {
"content": "ɡʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"323": {
"content": "ɯɯ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"324": {
"content": "dʒʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"325": {
"content": "ʂʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"327": {
"content": "ɵː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"328": {
"content": "uaiɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"329": {
"content": "tɕʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"330": {
"content": "ã",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"331": {
"content": "t^ː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"332": {
"content": "ẽː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"333": {
"content": "yɛ2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"334": {
"content": "cː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"335": {
"content": "i.1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"336": {
"content": "ɛʊ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"337": {
"content": "dˤdˤ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"338": {
"content": "dʒː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"339": {
"content": "i4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"340": {
"content": "ɡː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"341": {
"content": "yi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"342": {
"content": "ɕʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"343": {
"content": "ɟʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"344": {
"content": "pʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"345": {
"content": "dʑʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"346": {
"content": "yuɜ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"347": {
"content": "ua1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"348": {
"content": "ua4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"349": {
"content": "æiː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"350": {
"content": "ɐɐ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"351": {
"content": "ui",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"352": {
"content": "iou1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"353": {
"content": "ʊː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"354": {
"content": "a1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"355": {
"content": "iou4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"356": {
"content": "cʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"357": {
"content": "iɛ1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"358": {
"content": "yə2",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"359": {
"content": "ɖʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"360": {
"content": "ẽ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"361": {
"content": "ʒʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"362": {
"content": "ää",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"363": {
"content": "ər4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"364": {
"content": "iːː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"365": {
"content": "ɪː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"366": {
"content": "iɑ1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"367": {
"content": "ər1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"368": {
"content": "œː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"369": {
"content": "øi",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"370": {
"content": "ɪuː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"371": {
"content": "cʰcʰ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"372": {
"content": "əː1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"373": {
"content": "iː1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"375": {
"content": "kʰː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"376": {
"content": "o̞o̞",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"377": {
"content": "xʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"378": {
"content": "ou1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"379": {
"content": "iɛ4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"380": {
"content": "e̞e̞",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"381": {
"content": "y1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"382": {
"content": "dzː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"383": {
"content": "dʲʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"384": {
"content": "dʰː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"385": {
"content": "ɯᵝɯᵝ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"386": {
"content": "lː",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"387": {
"content": "uo1",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"388": {
"content": "i.4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"389": {
"content": "i:",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"390": {
"content": "yɛ5ʲ",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
},
"391": {
"content": "a4",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": false
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"phonemizer_backend": "espeak",
"phonemizer_lang": "en-us",
"replace_word_delimiter_char": " ",
"target_lang": null,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"unk_token": "<unk>",
"word_delimiter_token": "|"
}