Skip to content

Commit

Permalink
vietnamese/central retrain
Browse files Browse the repository at this point in the history
  • Loading branch information
neurlang authored and Your Name committed Oct 12, 2024
1 parent e78d022 commit 75d2650
Show file tree
Hide file tree
Showing 2 changed files with 226 additions and 78 deletions.
304 changes: 226 additions & 78 deletions dicts/vietnamese/central/language.json
Original file line number Diff line number Diff line change
@@ -1,130 +1,278 @@
{"Map":{"(":[],
",":["˧˥","˩˧","˦˨","˨ˀ˩ʔ","˧˩˨"],
"-":["˧˥","˦˨"],
";":["˦˨","˧˩˨","˨ˀ˩ʔ","˧˥","˩˧"],
"a":["a","ə˧˥","ə˧˩˨","ă","ə˩˧","ə˦˨","ə˨ˀ˩ʔ"],
"ay":[],
{"Map":{"":[],
"\"\"không\"\"":["xoŋm˧˥"],
"(anh)":["an˧˥"],
"(dân":["jɤ̆ŋ˧˥"],
"(quá":["wa˩˧"],
")":["˦˨","˧˩˨","˩˧","˧˥"],
",":["˩˧","˨ˀ˩ʔ","˧˥","˦˨","˧˩˨","˦˥"],
"-":["˧˥","˦˥","˦˨","˨ˀ˩ʔ"],
"-câu":["kɤ̆w˧˥"],
"-gích":["ɣit˦˥"],
"-lai":["laj˧˥"],
"-len":["lɛŋ˧˥"],
"-man":["maŋ"],
"-men":["mɛŋ˧˥"],
"-nát":["nak˦˥"],
"-phát":["fak˦˥"],
"-rút":["ʐukp˦˥"],
"-rập":["ʐɤ̆p˨ˀ˩ʔ"],
"-tinh":["tin˧˥"],
"-trui":["ʈuj"],
"-tràng":["ʈaŋ"],
"-tông":["toŋm˧˥"],
"-vanh":["jan˧˥"],
"-xinh":["sin˧˥"],
"-xít":["sit˦˥"],
"-ôn":["oŋm˧˥"],
"-đông":["doŋm˧˥"],
";":["˨ˀ˩ʔ","˦˨","˧˩˨","˧˥","p˦˥","˩˧","˦˥"],
"a":["a˧˥","a","ə˩˧","ă","ə˨ˀ˩ʔ","ə˧˩˨","ə˦˨","ə˧˥"],
"ai":["aj˧˥"],
"ang":["aŋ˧˥"],
"anh":["an˧˥"],
"ao":["aw˧˥"],
"ay":["ăj˧˥"],
"b":["b"],
"c":["k","k˦˥","k˨ˀ˩ʔ","kp˦˥","kp˨ˀ˩ʔ"],
"ch":["c","t˦˥","k˨ˀ˩ʔ","k˦˥","t˨ˀ˩ʔ"],
"c":["k","t˦˥","t"],
"ch":["c","t˦˥","t˨ˀ˩ʔ","k˧˩˨"],
"d":["j"],
"e":["ɛ","e","e˦˨","e˧˩˨","e˩˧"],
"eo":["eo˧˥","ew˧˥"],
"g":["ɣ"],
"e":["ɛ˧˥","ɛ","e˧˥","e˧˩˨","e˩˧","e"],
"en":["ɛŋ˧˥","en˧˥"],
"eo":["eo˧˥","ew˧˥","ew˩˧"],
"g":["ɣ","z"],
"gi":["j"],
"h":["h","˧˥"],
"i":["j˧˥","j˩˧","j˦˨","j˧˩˨","j˨ˀ˩ʔ","i","i˧˥"],
"ia":["iə˧˥"],
"iê":[""],
"iế":[""],
"iề":[""],
"iể":[""],
"iểu":["iəw˧˩˨"],
"iễ":[""],
"iễu":["iəw˧˩˨"],
"iệ":[""],
"h":["h","˧˩˨","˨ˀ˩ʔ"],
"he":["ɛ˧˥","ɛ"],
"hen":["hɛŋ˧˥","ɛŋ˧˥"],
"heo":["heo˧˥"],
"hi":["i˧˥","i"],
"hè":["ɛ˦˨",""],
"hèn":["ɛŋ˦˨"],
"hèo":["heo˦˨","eo˦˨"],
"hé":["ɛ˩˧","ɛ"],
"héo":["heo˩˧"],
"hê":["e˧˥","he","e","ɛ"],
"hênh":["hen˧˥","en˧˥"],
"hì":["i˦˨","i"],
"hình":["hin˦˨"],
"hình,":["hin˦˨"],
"hí":["hi","i˩˧"],
"hĩ":["i˧˩˨"],
"hĩa":["iə˧˩˨"],
"hĩa,":["iə˧˩˨"],
"hẹ":["ɛ˨ˀ˩ʔ","","ɛ"],
"hẹn":["ɛŋ˨ˀ˩ʔ"],
"hẹo":["eo˨ˀ˩ʔ"],
"hẹt":[],
"hẻ":["ɛ˧˩˨",""],
"hẻo":["heo˧˩˨"],
"hẽn":["ɛŋ˧˩˨"],
"hế":["e˩˧","he"],
"hếch":["et˦˥"],
"hề":["e˦˨","ɛ","e"],
"hềnh":["en˦˨"],
"hể":["e˧˩˨","","e"],
"hểnh":["en˧˩˨"],
"hễnh":["en˧˩˨"],
"hệ":["e˨ˀ˩ʔ","e"],
"hệch":["et˨ˀ˩ʔ"],
"hỉ":["i˧˩˨","i"],
"hỉnh":["hin˧˩˨"],
"hị":["i˨ˀ˩ʔ"],
"hịch":["it˨ˀ˩ʔ"],
"i":["i˧˥","j˨ˀ˩ʔ","i","j˩˧","j˦˨","j˧˩˨","j˧˥"],
"iên":["iəŋ˧˥"],
"k":["k"],
"kh":["x"],
"l":["l"],
"m":["m"],
"n":["n","ŋ˩˧","ŋ˧˥","ŋ˦˨","ŋ˨ˀ˩ʔ","ŋ˧˩˨","ŋm˧˥","ŋm˦˨","ŋm˧˩˨","ŋm˩˧","n˧˥","ŋm˨ˀ˩ʔ","n˦˨","n˩˧","n˨ˀ˩ʔ","n˧˩˨"],
"ng":["ŋ","ŋ˧˥","ŋ˦˨","ŋ˧˩˨","ŋm˧˥","ŋm˦˨","ŋ˩˧","ŋ˨ˀ˩ʔ","ŋm˧˩˨","ŋm˩˧","ŋm˨ˀ˩ʔ","n˧˥"],
"nh":["ɲ","n˧˥","n˩˧","n˦˨","n˨ˀ˩ʔ","n˧˩˨"],
"o":["w","ɔ"],
"n":["n","ŋ˦˨","ŋ˨ˀ˩ʔ","ŋ˩˧","ŋ˧˩˨","ŋm˩˧","ŋm˧˥","ŋm˧˩˨","ŋm˨ˀ˩ʔ","ŋm˦˨","ŋ˧˥"],
"n)":["ŋ˦˨"],
"ng":["ŋ","ŋm˩˧","ŋ˧˩˨","ŋ˩˧","n˧˩˨","n˦˨","n˩˧","n˧˥","n"],
"nh":["ɲ","n˧˩˨","n˨ˀ˩ʔ","n˩˧","n˦˨","n˧˥"],
"o":["ɔ˧˥","w","ɔ"],
"oi":["ɔj˧˥"],
"ong":["ɔŋm˧˥","ŋm˧˥"],
"p":["p˦˥","p˨ˀ˩ʔ","p"],
"ph":["f"],
"qu":["w"],
"qua":["wa",""],
"quay":["wăj˧˥"],
"quen":["wɛŋ˧˥"],
"queng":["wɛŋ˧˥"],
"queo":["weo˧˥"],
"qui":["wi˧˥"],
"quài":["waj˦˨"],
"quàng":["waŋ˦˨"],
"quành":["wan˦˨"],
"quách":["wak˦˥"],
"quái":["waj˩˧","waj"],
"quán":["waŋ˩˧"],
"quáng":["waŋ˩˧","waŋ"],
"quánh":["wan˩˧"],
"quát":["wak˦˥"],
"quân":["wɤ̆ŋ˧˥"],
"quèn":["wɛŋ˦˨"],
"quèo":["weo˦˨"],
"quét":["wɛk˦˥"],
"quít":["wit˦˥"],
"quăn":["wăŋ˧˥"],
"quăng":["wăŋ˧˥"],
"quải":["waj˧˩˨"],
"quảy":["wăj˧˩˨"],
"quấn":["wɤ̆ŋ˩˧"],
"quận":["wɤ̆ŋ˨ˀ˩ʔ"],
"quẳng":["wăŋ˧˩˨"],
"quẹo":["weo˨ˀ˩ʔ"],
"quềnh":["wen˦˨"],
"quố":["wo"],
"quỷ":["wi˧˩˨"],
"quỹ":["wi˧˩˨"],
"r":["ʐ"],
"s":["ʂ"],
"t":["t","k˦˥","k˨ˀ˩ʔ","kp˦˥","kp˨ˀ˩ʔ","t˦˥","t˨ˀ˩ʔ"],
"t":["t","k˦˥","k˨ˀ˩ʔ","kp˨ˀ˩ʔ","kp˦˥"],
"t)":["kp˨ˀ˩ʔ"],
"th":[""],
"tr":["ʈ"],
"u":["w","u"],
"u":["u˧˥","w","u"],
"ua":["uə˧˥"],
"ui":["uj˧˥"],
"un":["uŋm˧˥"],
"ung":[],
"uố":[""],
"uộ":[],
"v":["j"],
"x":["s"],
"y":["j˧˩˨","j˧˥","j˦˨","j˩˧","i˧˥","j˨ˀ˩ʔ","i"],
"yê":["",""],
"yế":["",""],
"yề":[""],
"yể":["",""],
"yệ":[""],
"y":["j˧˥","j˦˨","j˩˧","i","j˧˩˨","j˨ˀ˩ʔ"],
"y)":["j˦˨"],
"Â":["ɤ̆"],
"à":["a","ă"],
"á":["a","ă"],
"Ê":["e"],
"à":["a˦˨","a","ă"],
"ài":["aj˦˨"],
"àng":["aŋ˦˨"],
"ành":["an˦˨"],
"ào":["aw˦˨"],
"á":["a˩˧","a","ă"],
"ách":["ak˦˥"],
"ái":["aj˩˧"],
"án":["aŋ˩˧"],
"ánh":["an˩˧"],
"áo":["aw˩˧"],
"át":["ak˦˥"],
"áy":["ăj˩˧"],
"â":["ɤ̆"],
"ã":["a","ă"],
"è":["ɛ","e˦˨","e","ɛ˦˨"],
"ân":["ɤ̆ŋ˧˥"],
"âu":["ɤ̆w˧˥"],
"ã":["a˧˩˨","a","ă"],
"è":["ɛ˦˨","ɛ","e˦˨"],
"èn":["ɛŋ˦˨","en˦˨"],
"èo":["eo˦˨","ew˦˨"],
"é":["ɛ","e","e˩˧","ɛ˩˧"],
"éo":["eo˩˧"],
"ê":["e","ɛ"],
"é":["ɛ˩˧","ɛ","e˩˧"],
"éo":["eo˩˧","ew˩˧"],
"ét":["ɛk˦˥","et˦˥"],
"ê":["e˧˥","e","ə","ɛ"],
"ì":["i˦˨","i"],
"ìa":["iə˦˨"],
"ình":[],
"í":["i"],
"ía":["iə˩˧"],
"ò":["ɔ","w"],
"ó":["ɔ","w"],
"ô":["o","ə"],
"õ":["ɔ"],
"ù":["u"],
"ít":["it˦˥"],
"ò":["ɔ","ɔ˦˨","w"],
"òe":["we˦˨"],
"òng":["ɔŋm˦˨","ŋm˦˨"],
"ó":["ɔ˩˧","ɔ","w"],
"óc":["ɔkp˦˥","kp˦˥"],
"ót":["ɔkp˦˥"],
"ô":["o˧˥","o","ə"],
"ôi":["oj˧˥","əj˧˥"],
"ôn":["əŋ˧˥","oŋm˧˥"],
"ông":["oŋm˧˥","əŋ˧˥"],
"õ":["ɔ","w"],
"ù":["u˦˨","u"],
"ùn":["uŋm˦˨"],
"ùng":["uŋm˦˨"],
"ú":["u"],
"út":["ukp˦˥"],
"ý":["i"],
"ă":["ă"],
"ăn":["ăŋ˧˥"],
"ăng":["ăŋ˧˥"],
"Đ":["d"],
"đ":["d"],
"ĩ":["i","i˧˩˨"],
"ĩa":["iə˧˩˨"],
"ĩ":["i"],
"ũ":["u"],
"ơ":["ɤ","ə"],
"ơ":["ɤ˧˥","ɤ","ə˧˥"],
"ơi":["ɤj˧˥"],
"ơn":["ɤŋ˧˥"],
"ư":["ɯ"],
"ạ":["a","ă"],
"ả":["a","ă"],
"ưa":[],
"ưng":["ɯŋ˧˥"],
"ươ":["ɯə"],
"ương":["ɯəŋ˧˥"],
"ướ":["ɯə"],
"ườ":["ɯə"],
"ường":["ɯəŋ˦˨"],
"ưở":["ɯə"],
"ưỡ":["ɯə"],
"ượ":["ɯə"],
"ạ":["a˨ˀ˩ʔ","a","ă"],
"ạch":["ak˨ˀ˩ʔ"],
"ả":["a˧˩˨","a","ă"],
"ải":["aj˧˩˨"],
"ảy":["ăj˧˩˨"],
"ấ":["ɤ̆"],
"ấn":["ɤ̆ŋ˩˧"],
"ấp":[],
"ấu":["ɤ̆w˩˧"],
"ầ":["ɤ̆"],
"ầu":["ɤ̆w˦˨"],
"ẩ":["ɤ̆"],
"ẫ":["ɤ̆"],
"ậ":["ɤ̆"],
"ận":["ɤ̆ŋ˨ˀ˩ʔ"],
"ắ":["ă"],
"ằ":["ă"],
"ẳ":["ă"],
"ẳn":["ăŋ˧˩˨"],
"ẵ":["ă"],
"ặ":["ă"],
"ẹ":["ɛ"],
"ẹ":["ɛ","e"],
"ẹo":["eo˨ˀ˩ʔ"],
"ẻ":["ɛ˧˩˨","ɛ","e˧˩˨"],
"ẻ":["ɛ˧˩˨","ɛ","e˧˩˨","e"],
"ẻng":["en˧˩˨","ɛŋ˧˩˨"],
"ẻo":["eo˧˩˨","ew˧˩˨"],
"ẽ":["ɛ˧˩˨","ɛ"],
"ẽo":["eo˧˩˨"],
"ế":["e","ɛ","e˩˧"],
"ề":["e","ɛ","e˦˨"],
"ể":["e˧˩˨","e","ɛ"],
"ễ":["e","e˧˩˨","ɛ"],
"ệ":["e","ɛ"],
"ế":["ə","e","ɛ"],
"ề":["e˦˨","ə","e","ɛ"],
"ềnh":["en˦˨"],
"ể":["ə","e˧˩˨","e","ɛ"],
"ễ":["ə","ɛ","e˧˩˨","e"],
"ệ":["e","ə","ɛ"],
"ỉ":["i˧˩˨","i"],
"ỉa":["iə˧˩˨"],
"ị":["i","i˨ˀ˩ʔ"],
"ịa":["iə˨ˀ˩ʔ"],
"ọ":["ɔ","w"],
"ị":["i˨ˀ˩ʔ","i"],
"ọ":["ɔ˨ˀ˩ʔ","ɔ","w"],
"ọc":["ɔkp˨ˀ˩ʔ","kp˨ˀ˩ʔ"],
"ỏ":["ɔ","w"],
"ố":["o","ə"],
"ố":["o"],
"ồ":["o","ə"],
"ổ":["o","o˧˩˨","ə"],
"ỗ":["o˧˩˨","o","ə"],
"ộ":["o","ə"],
"ớ":["ɤ","ə"],
"ờ":["ɤ","ə","ə˦˨"],
"ở":["ɤ˧˩˨","ɤ","ə"],
"ỡ":["ɤ˧˩˨","ə","ɤ"],
"ợ":["ɤ","ə"],
"ụ":["u"],
"ủ":["u"],
"ồn":["oŋm˦˨","əŋ˦˨"],
"ồng":["oŋm˦˨","əŋ˦˨"],
"ổ":["o˧˩˨","o","ə"],
"ỗ":["o˧˩˨","ə","o"],
"ộ":["o"],
"ớ":["ɤ˩˧","ɤ"],
"ờ":["ɤ˦˨","ɤ","ə˦˨"],
"ở":["ɤ","ɤ˧˩˨","ə˧˩˨","ə"],
"ỡ":["ɤ˧˩˨","ɤ"],
"ợ":["ɤ"],
"ụ":["u˨ˀ˩ʔ","u"],
"ủ":["u˧˩˨","u"],
"ứ":["ɯ"],
"ừ":["ɯ"],
"ừ":["ɯ˦˨","ɯ"],
"ừng":["ɯŋ˦˨"],
"ử":["ɯ"],
"ữ":["ɯ"],
"ự":["ɯ"],
"ỳ":["i˦˨","i"],
"ỵ":["i˨ˀ˩ʔ","i"],
"ỷ":["i˧˩˨"],
"ỹ":["i˧˩˨"]},"SrcMulti":null,"DstMulti":null,"SrcMultiSuffix":null,"DstMultiSuffix":["ː"],
"DropLast":null,"SplitBefore":null,"SplitAfter":null,"PrePhonWordSteps":[{"Trim":".,"},{"ToLower":true}]}
"DstMultiPrefix":null,"DropLast":null,"SplitBefore":null,"SplitAfter":null,"PrePhonWordSteps":[{"Trim":".,"},{"ToLower":true}]}
Binary file modified dicts/vietnamese/central/weights1.json.lzw
Binary file not shown.

0 comments on commit 75d2650

Please sign in to comment.