Spaces:
Running
Running
{ | |
"version": "1.0", | |
"truncation": null, | |
"padding": null, | |
"added_tokens": [ | |
{ | |
"id": 0, | |
"content": "[UNK]", | |
"single_word": false, | |
"lstrip": false, | |
"rstrip": false, | |
"normalized": false, | |
"special": true | |
}, | |
{ | |
"id": 1, | |
"content": "[CLS]", | |
"single_word": false, | |
"lstrip": false, | |
"rstrip": false, | |
"normalized": false, | |
"special": true | |
}, | |
{ | |
"id": 2, | |
"content": "[SEP]", | |
"single_word": false, | |
"lstrip": false, | |
"rstrip": false, | |
"normalized": false, | |
"special": true | |
}, | |
{ | |
"id": 3, | |
"content": "[PAD]", | |
"single_word": false, | |
"lstrip": false, | |
"rstrip": false, | |
"normalized": false, | |
"special": true | |
}, | |
{ | |
"id": 4, | |
"content": "[MASK]", | |
"single_word": false, | |
"lstrip": false, | |
"rstrip": false, | |
"normalized": false, | |
"special": true | |
} | |
], | |
"normalizer": null, | |
"pre_tokenizer": { | |
"type": "Whitespace" | |
}, | |
"post_processor": null, | |
"decoder": null, | |
"model": { | |
"type": "BPE", | |
"dropout": null, | |
"unk_token": "[UNK]", | |
"continuing_subword_prefix": null, | |
"end_of_word_suffix": null, | |
"fuse_unk": false, | |
"byte_fallback": false, | |
"vocab": { | |
"[UNK]": 0, | |
"[CLS]": 1, | |
"[SEP]": 2, | |
"[PAD]": 3, | |
"[MASK]": 4, | |
"!": 5, | |
"#": 6, | |
"*": 7, | |
",": 8, | |
"-": 9, | |
".": 10, | |
"=": 11, | |
"?": 12, | |
"N": 13, | |
"Q": 14, | |
"^": 15, | |
"_": 16, | |
"`": 17, | |
"a": 18, | |
"b": 19, | |
"d": 20, | |
"e": 21, | |
"f": 22, | |
"g": 23, | |
"h": 24, | |
"i": 25, | |
"j": 26, | |
"k": 27, | |
"l": 28, | |
"m": 29, | |
"n": 30, | |
"o": 31, | |
"p": 32, | |
"s": 33, | |
"t": 34, | |
"u": 35, | |
"v": 36, | |
"w": 37, | |
"x": 38, | |
"y": 39, | |
"z": 40, | |
"~": 41, | |
"æ": 42, | |
"ç": 43, | |
"ð": 44, | |
"ŋ": 45, | |
"ɑ": 46, | |
"ɔ": 47, | |
"ə": 48, | |
"ɛ": 49, | |
"ɥ": 50, | |
"ɪ": 51, | |
"ɫ": 52, | |
"ɯ": 53, | |
"ɸ": 54, | |
"ɹ": 55, | |
"ɾ": 56, | |
"ʃ": 57, | |
"ʊ": 58, | |
"ʑ": 59, | |
"ʒ": 60, | |
"ʰ": 61, | |
"ˈ": 62, | |
"ˌ": 63, | |
"θ": 64, | |
"…": 65, | |
"⁼": 66, | |
"↑": 67, | |
"→": 68, | |
"↓": 69, | |
"ɯəj": 70, | |
"ɤ̆j": 71, | |
"ʷiə": 72, | |
"ɤ̆w": 73, | |
"ɯəw": 74, | |
"ʷet": 75, | |
"iəw": 76, | |
"uəj": 77, | |
"ʷen": 78, | |
"tʰw": 79, | |
"ʷɤ̆": 80, | |
"ʷiu": 81, | |
"kwi": 82, | |
"ŋ͡m": 83, | |
"k͡p": 84, | |
"cw": 85, | |
"jw": 86, | |
"uə": 87, | |
"eə": 88, | |
"bw": 89, | |
"oj": 90, | |
"ʷi": 91, | |
"vw": 92, | |
"ăw": 93, | |
"ʈw": 94, | |
"ʂw": 95, | |
"aʊ": 96, | |
"fw": 97, | |
"ɛu": 98, | |
"tʰ": 99, | |
"tʃ": 100, | |
"ɔɪ": 101, | |
"xw": 102, | |
"ʷɤ": 103, | |
"ɤ̆": 104, | |
"ŋw": 105, | |
"ʊə": 106, | |
"zi": 107, | |
"ʷă": 108, | |
"dw": 109, | |
"eɪ": 110, | |
"aɪ": 111, | |
"ew": 112, | |
"iə": 113, | |
"ɣw": 114, | |
"zw": 115, | |
"ɯj": 116, | |
"ʷɛ": 117, | |
"ɯw": 118, | |
"ɤj": 119, | |
"ɔ:": 120, | |
"əʊ": 121, | |
"ʷa": 122, | |
"mw": 123, | |
"ɑ:": 124, | |
"hw": 125, | |
"ɔj": 126, | |
"uj": 127, | |
"lw": 128, | |
"ɪə": 129, | |
"ăj": 130, | |
"u:": 131, | |
"aw": 132, | |
"ɛj": 133, | |
"iw": 134, | |
"aj": 135, | |
"ɜ:": 136, | |
"kw": 137, | |
"nw": 138, | |
"t∫": 139, | |
"ɲw": 140, | |
"eo": 141, | |
"sw": 142, | |
"tw": 143, | |
"ʐw": 144, | |
"iɛ": 145, | |
"ʷe": 146, | |
"i:": 147, | |
"ɯə": 148, | |
"dʒ": 149, | |
"ɲ": 150, | |
"ʌ": 151, | |
"1": 152, | |
"∫": 153, | |
"3": 154, | |
"ɣ": 155, | |
"ʧ": 156, | |
"6": 157, | |
"ʐ": 158, | |
"ă": 159, | |
"ɤ": 160, | |
"2": 161, | |
"ʤ": 162, | |
"ɒ": 163, | |
"ʂ": 164, | |
"5": 165, | |
" ": 166, | |
"c": 167, | |
"ʈ": 168, | |
"4": 169, | |
"r": 170, | |
":": 171, | |
"η": 172, | |
";": 173, | |
"'": 174 | |
}, | |
"merges": [ | |
] | |
} | |
} |