diff --git "a/data/Austro-Asiatic.json" "b/data/Austro-Asiatic.json" new file mode 100644--- /dev/null +++ "b/data/Austro-Asiatic.json" @@ -0,0 +1,3109 @@ +{ + "name": "Austro-Asiatic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "bottom", + "children": [ + { + "name": "Mon-Khmer", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "bottom", + "children": [ + { + "name": "Aslian", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Jah Hut", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Jah Hut", + "iso_1_code": null, + "iso_3_code": "jah", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "North Aslian", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Chewong", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Cheq Wong", + "iso_1_code": null, + "iso_3_code": "cwg", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Eastern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Batek", + "iso_1_code": null, + "iso_3_code": "btq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Jehai", + "iso_1_code": null, + "iso_3_code": "jhi", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Minriq", + "iso_1_code": null, + "iso_3_code": "mnq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mintil", + "iso_1_code": null, + "iso_3_code": "mzt", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Tonga", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Ten\u2019edn", + "iso_1_code": null, + "iso_3_code": "tnz", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Western", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Kintaq", + "iso_1_code": null, + "iso_3_code": "knq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kensiu", + "iso_1_code": null, + "iso_3_code": "kns", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Senoic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Lanoh", + "iso_1_code": null, + "iso_3_code": "lnh", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sab\u00fcm", + "iso_1_code": null, + "iso_3_code": "sbo", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Semai", + "iso_1_code": null, + "iso_3_code": "sea", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Semnam", + "iso_1_code": null, + "iso_3_code": "ssm", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Temiar", + "iso_1_code": null, + "iso_3_code": "tea", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "South Aslian", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Mah Meri", + "iso_1_code": null, + "iso_3_code": "mhe", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Semelai", + "iso_1_code": null, + "iso_3_code": "sza", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Semaq Beri", + "iso_1_code": null, + "iso_3_code": "szc", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Temoq", + "iso_1_code": null, + "iso_3_code": "tmo", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Eastern Mon-Khmer", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Bahnaric", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Central Bahnaric", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Alak", + "iso_1_code": null, + "iso_3_code": "alk", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Bahnar", + "iso_1_code": null, + "iso_3_code": "bdq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Romam", + "iso_1_code": null, + "iso_3_code": "rmx", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tampuan", + "iso_1_code": null, + "iso_3_code": "tpu", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "East Bahnaric", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Cua", + "iso_1_code": null, + "iso_3_code": "cua", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "North Bahnaric", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Katua", + "iso_1_code": null, + "iso_3_code": "kta", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kachok", + "iso_1_code": null, + "iso_3_code": "xkk", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "East", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Kayong", + "iso_1_code": null, + "iso_3_code": "kxy", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Takua", + "iso_1_code": null, + "iso_3_code": "tkz", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "West", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Trieng", + "iso_1_code": null, + "iso_3_code": "stg", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Talieng", + "iso_1_code": null, + "iso_3_code": "tdf", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Duan", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Halang Doan", + "iso_1_code": null, + "iso_3_code": "hld", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Jeh-Halang", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Halang", + "iso_1_code": null, + "iso_3_code": "hal", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Jeh", + "iso_1_code": null, + "iso_3_code": "jeh", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Rengao", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Rengao", + "iso_1_code": null, + "iso_3_code": "ren", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Sedang-Todrah", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Sedang", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Hre", + "iso_1_code": null, + "iso_3_code": "hre", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sedang", + "iso_1_code": null, + "iso_3_code": "sed", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Todrah-Monom", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Monom", + "iso_1_code": null, + "iso_3_code": "moo", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Todrah", + "iso_1_code": null, + "iso_3_code": "tdr", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + } + ] + }, + { + "name": "South Bahnaric", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Stieng, Budeh", + "iso_1_code": null, + "iso_3_code": "stt", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sre-Mnong", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Mnong", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Eastern Mnong", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Mnong, Eastern", + "iso_1_code": null, + "iso_3_code": "mng", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Southern-Central Mnong", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Mnong, Central", + "iso_1_code": null, + "iso_3_code": "cmo", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mnong, Southern", + "iso_1_code": null, + "iso_3_code": "mnn", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kraol", + "iso_1_code": null, + "iso_3_code": "rka", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Sre", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Maa", + "iso_1_code": null, + "iso_3_code": "cma", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Koho", + "iso_1_code": null, + "iso_3_code": "kpm", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Stieng-Chrau", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Chrau", + "iso_1_code": null, + "iso_3_code": "crw", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mel-Khaonh", + "iso_1_code": null, + "iso_3_code": "hkn", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Stieng, Bulo", + "iso_1_code": null, + "iso_3_code": "sti", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "West Bahnaric", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Lavi", + "iso_1_code": null, + "iso_3_code": "lvi", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Brao-Kravet", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Brao", + "iso_1_code": null, + "iso_3_code": "brb", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Krung", + "iso_1_code": null, + "iso_3_code": "krr", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kavet", + "iso_1_code": null, + "iso_3_code": "krv", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sou", + "iso_1_code": null, + "iso_3_code": "sqq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Laven", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Laven", + "iso_1_code": null, + "iso_3_code": "lbo", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Nyaheun", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Nyaheun", + "iso_1_code": null, + "iso_3_code": "nev", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Oi-The", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Oy", + "iso_1_code": null, + "iso_3_code": "oyb", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sapuan", + "iso_1_code": null, + "iso_3_code": "spu", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "Katuic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Central Katuic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Ta\u2019oih", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Ir", + "iso_1_code": null, + "iso_3_code": "irr", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ong", + "iso_1_code": null, + "iso_3_code": "oog", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ta\u2019oih, Upper", + "iso_1_code": null, + "iso_3_code": "tth", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ta\u2019oih, Lower", + "iso_1_code": null, + "iso_3_code": "tto", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "East Katuic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Katu-Pacoh", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Katu, Eastern", + "iso_1_code": null, + "iso_3_code": "ktv", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Katu, Western", + "iso_1_code": null, + "iso_3_code": "kuf", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Pacoh", + "iso_1_code": null, + "iso_3_code": "pac", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Phuong", + "iso_1_code": null, + "iso_3_code": "phg", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tareng", + "iso_1_code": null, + "iso_3_code": "tgr", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Ngeq-Nkriang", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Kriang", + "iso_1_code": null, + "iso_3_code": "ngt", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "West Katuic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Bru", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Bru, Eastern", + "iso_1_code": null, + "iso_3_code": "bru", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Bru, Western", + "iso_1_code": null, + "iso_3_code": "brv", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Katang, Northern", + "iso_1_code": null, + "iso_3_code": "ncq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Katang, Southern", + "iso_1_code": null, + "iso_3_code": "sct", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "So", + "iso_1_code": null, + "iso_3_code": "sss", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Khua", + "iso_1_code": null, + "iso_3_code": "xhv", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Kuay", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Kuay", + "iso_1_code": null, + "iso_3_code": "kdt", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Nyeu", + "iso_1_code": null, + "iso_3_code": "nyl", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "Khmer", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Khmer", + "iso_1_code": "km", + "iso_3_code": "khm", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Khmer, Northern", + "iso_1_code": null, + "iso_3_code": "kxm", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Pearic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Eastern", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Pear", + "iso_1_code": null, + "iso_3_code": "pcb", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Western", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Chong", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Chong", + "iso_1_code": null, + "iso_3_code": "cog", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Chung", + "iso_1_code": null, + "iso_3_code": "scq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Samre", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Somray", + "iso_1_code": null, + "iso_3_code": "smu", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Samre", + "iso_1_code": null, + "iso_3_code": "sxm", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Suoy", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Su\u2019ung", + "iso_1_code": null, + "iso_3_code": "syo", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + } + ] + }, + { + "name": "Monic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Mon", + "iso_1_code": null, + "iso_3_code": "mnw", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Nicobar", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Car", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Nicobarese, Car", + "iso_1_code": null, + "iso_3_code": "caq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Chowra-Teressa", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Chaura", + "iso_1_code": null, + "iso_3_code": "crv", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Teressa", + "iso_1_code": null, + "iso_3_code": "tef", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Great Nicobar", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Nicobarese, Southern", + "iso_1_code": null, + "iso_3_code": "nik", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Nancowry", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Nicobarese, Central", + "iso_1_code": null, + "iso_3_code": "ncb", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Shom Peng", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Shom Peng", + "iso_1_code": null, + "iso_3_code": "sii", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Northern Mon-Khmer", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Khasian", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "War-Jaintia", + "iso_1_code": null, + "iso_3_code": "aml", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Khasi", + "iso_1_code": null, + "iso_3_code": "kha", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Lyngngam", + "iso_1_code": null, + "iso_3_code": "lyg", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Pnar", + "iso_1_code": null, + "iso_3_code": "pbv", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Khmuic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Khao", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Khao", + "iso_1_code": null, + "iso_3_code": "xao", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Mal-Khmu\u2019", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Khmu\u2019", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Khuen", + "iso_1_code": null, + "iso_3_code": "khf", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Khmu", + "iso_1_code": null, + "iso_3_code": "kjg", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "O\u2019du", + "iso_1_code": null, + "iso_3_code": "tyh", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Mal-Prai", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Mal", + "iso_1_code": null, + "iso_3_code": "mlf", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Prai", + "iso_1_code": null, + "iso_3_code": "prt", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Mlabri", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Mlabri", + "iso_1_code": null, + "iso_3_code": "mra", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Xinh Mul", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Phong-Kniang", + "iso_1_code": null, + "iso_3_code": "pnx", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Puoc", + "iso_1_code": null, + "iso_3_code": "puo", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Mang", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Mang", + "iso_1_code": null, + "iso_3_code": "zng", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Palaungic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Eastern Palaungic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Angkuic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Hu", + "iso_1_code": null, + "iso_3_code": "huo", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kon Keu", + "iso_1_code": null, + "iso_3_code": "kkn", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Man Met", + "iso_1_code": null, + "iso_3_code": "mml", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mok", + "iso_1_code": null, + "iso_3_code": "mqt", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Samtao", + "iso_1_code": null, + "iso_3_code": "stu", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tai Loi", + "iso_1_code": null, + "iso_3_code": "tlq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Muak Sa-aak", + "iso_1_code": null, + "iso_3_code": "ukk", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "U", + "iso_1_code": null, + "iso_3_code": "uuu", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kiorr", + "iso_1_code": null, + "iso_3_code": "xko", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Bit-Khang", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Bit", + "iso_1_code": null, + "iso_3_code": "bgk", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Bumang", + "iso_1_code": null, + "iso_3_code": "bvp", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kh\u00e1ng", + "iso_1_code": null, + "iso_3_code": "kjm", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Lametic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Con", + "iso_1_code": null, + "iso_3_code": "cno", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Rmeet", + "iso_1_code": null, + "iso_3_code": "lbn", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Waic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Bulang", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Blang", + "iso_1_code": null, + "iso_3_code": "blr", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Lawa", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Lawa, Western", + "iso_1_code": null, + "iso_3_code": "lcp", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Lawa, Eastern", + "iso_1_code": null, + "iso_3_code": "lwl", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Wa", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Wa, Parauk", + "iso_1_code": null, + "iso_3_code": "prk", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Awa", + "iso_1_code": null, + "iso_3_code": "vwa", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Wa, Vo", + "iso_1_code": null, + "iso_3_code": "wbm", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "Western Palaungic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Danau", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Danau", + "iso_1_code": null, + "iso_3_code": "dnu", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Palaung", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Palaung, Ruching", + "iso_1_code": null, + "iso_3_code": "pce", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Palaung, Shwe", + "iso_1_code": null, + "iso_3_code": "pll", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Palaung, Rumai", + "iso_1_code": null, + "iso_3_code": "rbb", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Riang", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Riang Lang", + "iso_1_code": null, + "iso_3_code": "ril", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Riang Lai", + "iso_1_code": null, + "iso_3_code": "yin", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + } + ] + }, + { + "name": "Palyu", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Bugan", + "iso_1_code": null, + "iso_3_code": "bbh", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Bolyu", + "iso_1_code": null, + "iso_3_code": "ply", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Southern Monic", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Nyahkur", + "iso_1_code": null, + "iso_3_code": "cbn", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Unclassified", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Kemiehua", + "iso_1_code": null, + "iso_3_code": "kfj", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kuanhua", + "iso_1_code": null, + "iso_3_code": "xnh", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Viet-Muong", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "bottom", + "children": [ + { + "name": "Chut", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Arem", + "iso_1_code": null, + "iso_3_code": "aem", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Maleng", + "iso_1_code": null, + "iso_3_code": "pkt", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Chut", + "iso_1_code": null, + "iso_3_code": "scb", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Cuoi", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Hung", + "iso_1_code": null, + "iso_3_code": "hnu", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Tho", + "iso_1_code": null, + "iso_3_code": "tou", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Muong", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Bo", + "iso_1_code": null, + "iso_3_code": "bgl", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Muong", + "iso_1_code": null, + "iso_3_code": "mtq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ngu\u00f4n", + "iso_1_code": null, + "iso_3_code": "nuo", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Thavung", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Aheu", + "iso_1_code": null, + "iso_3_code": "thm", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Vietnamese", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "bottom", + "children": [ + { + "name": "Vietnamese", + "iso_1_code": "vi", + "iso_3_code": "vie", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "own", + "children": [] + } + ] + } + ] + } + ] + }, + { + "name": "Munda", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "North Munda", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Kherwari", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Agariya", + "iso_1_code": null, + "iso_3_code": "agi", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Bijori", + "iso_1_code": null, + "iso_3_code": "bix", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kodaku", + "iso_1_code": null, + "iso_3_code": "ksz", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mundari", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Asuri", + "iso_1_code": null, + "iso_3_code": "asr", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Birhor", + "iso_1_code": null, + "iso_3_code": "biy", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Koda", + "iso_1_code": null, + "iso_3_code": "cdz", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kol", + "iso_1_code": null, + "iso_3_code": "ekl", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Ho", + "iso_1_code": null, + "iso_3_code": "hoc", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Korwa", + "iso_1_code": null, + "iso_3_code": "kfp", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Mundari", + "iso_1_code": null, + "iso_3_code": "unr", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Munda", + "iso_1_code": null, + "iso_3_code": "unx", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Santali", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Mahali", + "iso_1_code": null, + "iso_3_code": "mjx", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Santhali", + "iso_1_code": null, + "iso_3_code": "sat", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Turi", + "iso_1_code": null, + "iso_3_code": "trd", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Korku", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Korku", + "iso_1_code": null, + "iso_3_code": "kfq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "South Munda", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Kharia-Juang", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Juang", + "iso_1_code": null, + "iso_3_code": "jun", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Kharia", + "iso_1_code": null, + "iso_3_code": "khr", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Koraput Munda", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Gutob-Remo-Geta\u2019", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Geta\u2019", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Gata\u2019", + "iso_1_code": null, + "iso_3_code": "gaq", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Gutob-Remo", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Bondo", + "iso_1_code": null, + "iso_3_code": "bfw", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Gadaba, Bodo", + "iso_1_code": null, + "iso_3_code": "gbj", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + }, + { + "name": "Sora-Juray-Gorum", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Gorum", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Parenga", + "iso_1_code": null, + "iso_3_code": "pcj", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + }, + { + "name": "Sora-Juray", + "iso_1_code": null, + "iso_3_code": null, + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [ + { + "name": "Juray", + "iso_1_code": null, + "iso_3_code": "juy", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + }, + { + "name": "Sora", + "iso_1_code": null, + "iso_3_code": "srb", + "tokenizer": { + "name": "vietnamese", + "tokenizer": "SpaCyTokenizer(\"vi\")" + }, + "source": "down", + "children": [] + } + ] + } + ] + } + ] + } + ] + } + ] + } + ] +} \ No newline at end of file