From 3b3e5a94c20bcb64be43f1e3848122331af6b56f Mon Sep 17 00:00:00 2001 From: Isaac Chung Date: Wed, 27 Nov 2024 22:05:30 +0000 Subject: [PATCH] add back some unclassified lang codes --- mteb/language_family.json | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/mteb/language_family.json b/mteb/language_family.json index 408a196c0..5770aa671 100644 --- a/mteb/language_family.json +++ b/mteb/language_family.json @@ -6946,6 +6946,11 @@ "level0": "Bororoan", "level1": "Bororo-Otuke" }, + "bos": { + "level0": "Indo-European", + "level1": "Balto-Slavic", + "level2": "Slavic" + }, "bot": { "level0": "Central Sudanic", "level1": "Sara-Bongo-Bagirmi" @@ -14824,6 +14829,10 @@ "level1": "Eskimo", "level2": "Yupik" }, + "est": { + "level0": "Uralic", + "level1": "Finnic" + }, "esu": { "level0": "Eskimo-Aleut", "level1": "Eskimo", @@ -15118,6 +15127,17 @@ "level8": "Central-Northern Malaita", "level9": "North Malaitan" }, + "fas": { + "level0": "Indo-European", + "level1": "Classical Indo-European", + "level2": "Indo-Iranian", + "level3": "Iranian", + "level4": "Southwestern Iranian", + "level5": "Middle-Modern Persian", + "level6": "Modern Southwestern Iranian", + "level7": "Farsic-Caucasian Tat", + "level8": "Farsic" + }, "fau": { "level0": "Lakes Plain", "level1": "Tariku", @@ -19706,6 +19726,10 @@ "level9": "Central Eastern Aramaic", "level10": "Bohtan" }, + "hrv": { + "level0": "Indo-European", + "level1": "Balto-Slavic" + }, "hrx": { "level0": "Indo-European", "level1": "Classical Indo-European", @@ -48744,6 +48768,10 @@ "level8": "Sardo-Corsican", "level9": "Sardinian" }, + "srp": { + "level0": "Indo-European", + "level1": "Balto-Slavic" + }, "srq": { "level0": "Tupian", "level1": "Eastern Tupian", @@ -49416,6 +49444,13 @@ "svr": { "level0": "Bookkeeping" }, + "swa": { + "level0": "Atlantic-Congo", + "level1": "Volta-Congo", + "level2": "Benue-Congo", + "level3": "Bantoid", + "level4": "Southern Bantoid" + }, "swb": { "level0": "Atlantic-Congo", "level1": "Volta-Congo",