diff --git "a/frontend/public/results.json" "b/frontend/public/results.json" --- "a/frontend/public/results.json" +++ "b/frontend/public/results.json" @@ -75,5 +75,8143 @@ "translation_bleu": 0.31, "translation_chrf": 0.48 } + ], + "language_table": [ + { + "language_name": "English", + "speakers": 1636485840, + "family": "Indo-European", + "average": 0.51, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.65, + "language_modeling_chrf": 0.94, + "translation_bleu": 0.43, + "translation_chrf": 0.55 + }, + { + "language_name": "Chinese", + "speakers": 1304678914, + "family": "Sino-Tibetan", + "average": 0.5, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.65, + "language_modeling_chrf": 0.93, + "translation_bleu": 0.38, + "translation_chrf": 0.55 + }, + { + "language_name": "French", + "speakers": 278611507, + "family": "Indo-European", + "average": 0.46, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.53, + "language_modeling_chrf": 0.98, + "translation_bleu": 0.32, + "translation_chrf": 0.49 + }, + { + "language_name": "Hindi", + "speakers": 546882144, + "family": "Indo-European", + "average": 0.46, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.53, + "language_modeling_chrf": 0.95, + "translation_bleu": 0.32, + "translation_chrf": 0.49 + }, + { + "language_name": "Portuguese", + "speakers": 237496885, + "family": "Indo-European", + "average": 0.46, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.5, + "language_modeling_chrf": 0.97, + "translation_bleu": 0.31, + "translation_chrf": 0.49 + }, + { + "language_name": "Spanish", + "speakers": 493528077, + "family": "Indo-European", + "average": 0.45, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.53, + "language_modeling_chrf": 0.96, + "translation_bleu": 0.28, + "translation_chrf": 0.46 + }, + { + "language_name": "Urdu", + "speakers": 290790290, + "family": "Indo-European", + "average": 0.42, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.5, + "language_modeling_chrf": 0.93, + "translation_bleu": 0.24, + "translation_chrf": 0.42 + }, + { + "language_name": "Punjabi", + "speakers": 203571210, + "family": "Indo-European", + "average": 0.42, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.4, + "language_modeling_chrf": 0.87, + "translation_bleu": 0.34, + "translation_chrf": 0.49 + }, + { + "language_name": "Arabic", + "speakers": 351664197, + "family": "Afro-Asiatic", + "average": 0.42, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.43, + "language_modeling_chrf": 0.93, + "translation_bleu": 0.28, + "translation_chrf": 0.47 + }, + { + "language_name": "Bangla", + "speakers": 267193288, + "family": "Indo-European", + "average": 0.38, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.4, + "language_modeling_chrf": 0.9, + "translation_bleu": 0.2, + "translation_chrf": 0.41 + }, + { + "language_name": "Afar", + "speakers": 2119663, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Okanagan", + "speakers": 490, + "family": "Salishan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nzima", + "speakers": 293402, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Occitan", + "speakers": 2040398, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ojibwa", + "speakers": 23747, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Oji-Cree", + "speakers": 15078, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Odia", + "speakers": 42434880, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Oromo", + "speakers": 34897121, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nyamwezi", + "speakers": 1932242, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ossetic", + "speakers": 541444, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Osage", + "speakers": 0, + "family": "Siouan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Pangasinan", + "speakers": 1528534, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Pampanga", + "speakers": 2511163, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Papiamento", + "speakers": 211640, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Palauan", + "speakers": 16047, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Picard", + "speakers": 746330, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nyankole", + "speakers": 2724939, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Navajo", + "speakers": 166320, + "family": "Athabaskan-Eyak-Tlingit", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nyanja", + "speakers": 17026781, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ngiemboon", + "speakers": 388430, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Western Huasteca Nahuatl", + "speakers": 501735, + "family": "Uto-Aztecan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ngaju", + "speakers": 987996, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Niuean", + "speakers": 1120, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ao Naga", + "speakers": 305001, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Dutch", + "speakers": 31765645, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kwasio", + "speakers": 8878, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Norwegian Nynorsk", + "speakers": 1366860, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Norwegian", + "speakers": 5467440, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Naxi", + "speakers": 334565, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Northern Thai", + "speakers": 6621830, + "family": "Tai-Kadai", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nimadi", + "speakers": 1723917, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "N’Ko", + "speakers": 626370, + "family": "Artificial Language", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "South Ndebele", + "speakers": 903418, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Naskapi", + "speakers": 1395, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Northern Sotho", + "speakers": 5307578, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nuer", + "speakers": 591427, + "family": "Nilotic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nigerian Pidgin", + "speakers": 44945880, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Pijin", + "speakers": 561780, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Pennsylvania German", + "speakers": 129729, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rohingya", + "speakers": 1824082, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Riffian", + "speakers": 3692411, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rajbanshi", + "speakers": 133443, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rangpuri", + "speakers": 16274502, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Romansh", + "speakers": 42020, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kalo Finnish Romani", + "speakers": 5015, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sinte Romani", + "speakers": 24372, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Domari", + "speakers": 1613543, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tavringer Romani", + "speakers": 9488, + "family": "Speech Register", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rundi", + "speakers": 7475454, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ronga", + "speakers": 1023339, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Romanian", + "speakers": 22187408, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tae'", + "speakers": 293729, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rombo", + "speakers": 433291, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rotuman", + "speakers": 2527, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Russian", + "speakers": 195841151, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rusyn", + "speakers": 527075, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Roviana", + "speakers": 9591, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Riang (India)", + "speakers": 172392, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Romagnol", + "speakers": 0, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Plautdietsch", + "speakers": 90466, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rejang", + "speakers": 1228320, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Palatine German", + "speakers": 0, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lomwe", + "speakers": 2046678, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Pökoot", + "speakers": 369343, + "family": "Nilotic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Polish", + "speakers": 41077399, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Piedmontese", + "speakers": 6178, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Pontic", + "speakers": 392463, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Pohnpeian", + "speakers": 23560, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Maliseet-Passamaquoddy", + "speakers": 490, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Parsi-Dari", + "speakers": 864342, + "family": "Bookkeeping", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Prussian", + "speakers": 38, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Pashto", + "speakers": 53542641, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Punu", + "speakers": 200782, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Quechua", + "speakers": 11385851, + "family": "Quechuan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kʼicheʼ", + "speakers": 1200731, + "family": "Mayan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Chimborazo Highland Quichua", + "speakers": 963579, + "family": "Quechuan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rajasthani", + "speakers": 1326090, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Réunion Creole French", + "speakers": 559185, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Eastern Huasteca Nahuatl", + "speakers": 501735, + "family": "Uto-Aztecan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Newari", + "speakers": 1000821, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ndonga", + "speakers": 552315, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mende", + "speakers": 1813083, + "family": "Mande", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Maithili", + "speakers": 19249149, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Makasar", + "speakers": 1949290, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mandingo", + "speakers": 3511762, + "family": "Mande", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Masai", + "speakers": 1734738, + "family": "Nilotic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Central Mazahua", + "speakers": 437410, + "family": "Otomanguean", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Moksha", + "speakers": 297616, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Maguindanaon", + "speakers": 1310172, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mandar", + "speakers": 245664, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Meru", + "speakers": 2141116, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rwa", + "speakers": 128816, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hassaniyya", + "speakers": 7239, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Pattani Malay", + "speakers": 3448870, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Morisyen", + "speakers": 1241433, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mandjak", + "speakers": 121170, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Malagasy", + "speakers": 24260130, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Makhuwa-Meetto", + "speakers": 1354419, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Metaʼ", + "speakers": 130401, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Eastern Magar", + "speakers": 333607, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Magahi", + "speakers": 15913080, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mafa", + "speakers": 205313, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Madurese", + "speakers": 16822638, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Laz", + "speakers": 22965, + "family": "Kartvelian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lambadi", + "speakers": 3580443, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lombard", + "speakers": 3901518, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lingala", + "speakers": 3514491, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lao", + "speakers": 5138706, + "family": "Tai-Kadai", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mongo", + "speakers": 620858, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lozi", + "speakers": 1045596, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Northern Luri", + "speakers": 2020512, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lithuanian", + "speakers": 2488617, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Latgalian", + "speakers": 167429, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Luba-Katanga", + "speakers": 2340940, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Luba-Lulua", + "speakers": 9770880, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Luo (Kenya and Tanzania)", + "speakers": 5245734, + "family": "Nilotic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Luyia", + "speakers": 5888069, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Southern Luri", + "speakers": 1019080, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Latvian", + "speakers": 1147550, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Eastern Lawa", + "speakers": 6898, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Literary Chinese", + "speakers": 0, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mbunga", + "speakers": 819739, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Marshallese", + "speakers": 56879, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Māori", + "speakers": 137913, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Indus Kohistani", + "speakers": 326901, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Marwari", + "speakers": 15913080, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mentawai", + "speakers": 64086, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Manyika", + "speakers": 945510, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Burmese", + "speakers": 36559231, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Erzya", + "speakers": 439338, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Masaaba", + "speakers": 1254337, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mazanderani", + "speakers": 4246165, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nauru", + "speakers": 6930, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Min Nan Chinese", + "speakers": 26486380, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Neapolitan", + "speakers": 605306, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nama", + "speakers": 289308, + "family": "Khoe-Kwadi", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Norwegian Bokmål", + "speakers": 5468932, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Central Huasteca Nahuatl", + "speakers": 244435, + "family": "Uto-Aztecan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "North Ndebele", + "speakers": 1745556, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ndau", + "speakers": 3867046, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Low German", + "speakers": 11520008, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nepali", + "speakers": 20903374, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kita Maninkakan", + "speakers": 977670, + "family": "Mande", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Muscogee", + "speakers": 3992, + "family": "Muskogean", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mi'kmaw", + "speakers": 7916, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mundang", + "speakers": 277450, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Minangkabau", + "speakers": 8010780, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Macedonian", + "speakers": 1608565, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Malayalam", + "speakers": 43257484, + "family": "Dravidian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Masalit", + "speakers": 451060, + "family": "Maban", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mongolian", + "speakers": 6572846, + "family": "Mongolic-Khitan", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Manipuri", + "speakers": 1476591, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mon", + "speakers": 966114, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Innu-aimun", + "speakers": 12062, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mohawk", + "speakers": 1772, + "family": "Iroquoian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mossi", + "speakers": 8334160, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Marathi", + "speakers": 92826300, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Western Magar", + "speakers": 251722, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Western Mari", + "speakers": 29762, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mru", + "speakers": 29277, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Malay", + "speakers": 38097307, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Maltese", + "speakers": 457267, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mewari", + "speakers": 1286307, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kinyarwanda", + "speakers": 11083625, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Safaliba", + "speakers": 4108, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Central Okinawan", + "speakers": 966404, + "family": "Japonic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Muslim Tat", + "speakers": 22453, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tuvalu", + "speakers": 9868, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tasawaq", + "speakers": 7970, + "family": "Songhay", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tahitian", + "speakers": 91488, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tuvinian", + "speakers": 184239, + "family": "Turkic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Central Atlas Tamazight", + "speakers": 3485047, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Udmurt", + "speakers": 538544, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Uyghur", + "speakers": 8052967, + "family": "Turkic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ukrainian", + "speakers": 29348975, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ulithian", + "speakers": 2971, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Umbundu", + "speakers": 9431467, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mundari", + "speakers": 1252287, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Munda", + "speakers": 636523, + "family": "Bookkeeping", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Uzbek", + "speakers": 32792780, + "family": "Turkic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Vai", + "speakers": 131906, + "family": "Mande", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Venda", + "speakers": 1391759, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Venetian", + "speakers": 1380829, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Veps", + "speakers": 3543, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tumbuka", + "speakers": 1780514, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Northeastern Thai", + "speakers": 16554576, + "family": "Tai-Kadai", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Virgin Islands Creole English", + "speakers": 3113, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tooro", + "speakers": 821807, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kathoriya Tharu", + "speakers": 72787, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Talysh", + "speakers": 1000168, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tamashek", + "speakers": 1776965, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tswana", + "speakers": 6113428, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ménik", + "speakers": 3305, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tongan", + "speakers": 100790, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nyasa Tonga", + "speakers": 207727, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tok Pisin", + "speakers": 5154217, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Turkish", + "speakers": 80360704, + "family": "Turkic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Turoyo", + "speakers": 3035, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Taroko", + "speakers": 4721, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Torwali", + "speakers": 123756, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tsonga", + "speakers": 4880932, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tsakonian", + "speakers": 202, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tausug", + "speakers": 1200991, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tshangla", + "speakers": 117348, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tatar", + "speakers": 1984108, + "family": "Turkic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Vietnamese", + "speakers": 86222962, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "West Flemish", + "speakers": 1172070, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tokelau", + "speakers": 1285, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kangri", + "speakers": 2121744, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sherpa", + "speakers": 157705, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Yao", + "speakers": 722357, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Yapese", + "speakers": 6556, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Yangben", + "speakers": 2303, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Yemba", + "speakers": 443920, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Yiddish", + "speakers": 997214, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Yoruba", + "speakers": 28685568, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nheengatu", + "speakers": 26171, + "family": "Tupian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Yucateco", + "speakers": 861955, + "family": "Mayan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Cantonese", + "speakers": 79654759, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Zhuang", + "speakers": 4321462, + "family": "Tai-Kadai", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Zaghawa", + "speakers": 232364, + "family": "Saharan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ngazidja Comorian", + "speakers": 313124, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Zeelandic", + "speakers": 241926, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Standard Moroccan Tamazight", + "speakers": 7823574, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Negeri Sembilan Malay", + "speakers": 391825, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Zulu", + "speakers": 13973830, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Soga", + "speakers": 2292409, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mingrelian", + "speakers": 439670, + "family": "Kartvelian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Main-Franconian", + "speakers": 4809582, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Xhosa", + "speakers": 10182944, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Makhuwa", + "speakers": 3912766, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Votic", + "speakers": 0, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Võro", + "speakers": 70031, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Vunjo", + "speakers": 433291, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Walloon", + "speakers": 679801, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Walser", + "speakers": 11377, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Wolaytta", + "speakers": 1946034, + "family": "Ta-Ne-Omotic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Waray", + "speakers": 3166927, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Warlpiri", + "speakers": 2496, + "family": "Pama-Nyungan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Waddar", + "speakers": 2386962, + "family": "Dravidian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Wagdi", + "speakers": 1989135, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Wallisian", + "speakers": 9512, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ndzwani Comorian", + "speakers": 287736, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Wolof", + "speakers": 11025494, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mewati", + "speakers": 6100014, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Wu Chinese", + "speakers": 83641200, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Xavánte", + "speakers": 9951, + "family": "Nuclear-Macro-Je", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tsakhur", + "speakers": 16329, + "family": "Nakh-Daghestanian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Turkmen", + "speakers": 6870838, + "family": "Turkic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sanskrit", + "speakers": 15913, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Koyraboro Senni", + "speakers": 664816, + "family": "Songhay", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Samogitian", + "speakers": 0, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tachelhit", + "speakers": 6187736, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Shan", + "speakers": 3687984, + "family": "Tai-Kadai", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sinhala", + "speakers": 15564656, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sidamo", + "speakers": 3783955, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Slovak", + "speakers": 6680269, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Saraiki", + "speakers": 28020120, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Slovenian", + "speakers": 1973181, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lower Silesian", + "speakers": 11868, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Selayar", + "speakers": 144194, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Samoan", + "speakers": 252717, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Southern Sami", + "speakers": 296, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lule Sami", + "speakers": 1530, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Inari Sami", + "speakers": 613, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Skolt Sami", + "speakers": 613, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Shona", + "speakers": 11782503, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Noon", + "speakers": 37767, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sango", + "speakers": 2935521, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Seri", + "speakers": 901, + "family": null, + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Somali", + "speakers": 16911645, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sena", + "speakers": 1384517, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Laki", + "speakers": 645417, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Yakut", + "speakers": 453510, + "family": "Turkic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Samburu", + "speakers": 246228, + "family": "Nilotic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sasak", + "speakers": 2590152, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Santali", + "speakers": 7293495, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Saafi-Saafi", + "speakers": 236046, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Saurashtra", + "speakers": 384566, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sangu", + "speakers": 117106, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sardinian", + "speakers": 1060846, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sadri", + "speakers": 2386962, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sicilian", + "speakers": 511702, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Scots", + "speakers": 1644028, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sindhi", + "speakers": 40329510, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sassarese Sardinian", + "speakers": 106085, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Southern Kurdish", + "speakers": 3142162, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Northern Sami", + "speakers": 51530, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Cebaara Senoufo", + "speakers": 1181687, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Soninke", + "speakers": 1153651, + "family": "Mande", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Southern Thai", + "speakers": 5518192, + "family": "Tai-Kadai", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tiv", + "speakers": 3424448, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Silesian", + "speakers": 497670, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Eastern Tamang", + "speakers": 130410, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tagbanwa", + "speakers": 10045, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tulu", + "speakers": 1989135, + "family": "Dravidian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tai Nüa", + "speakers": 264864, + "family": "Tai-Kadai", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Western Tamang", + "speakers": 394263, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Thulung", + "speakers": 36393, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Telugu", + "speakers": 95478480, + "family": "Dravidian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Timne", + "speakers": 1722482, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Teso", + "speakers": 2082973, + "family": "Nilotic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tetum", + "speakers": 816395, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tajik", + "speakers": 9644223, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Thai", + "speakers": 55181920, + "family": "Tai-Kadai", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Dangaura Tharu", + "speakers": 606558, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kochila Tharu", + "speakers": 303279, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rana Tharu", + "speakers": 363935, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tigrinya", + "speakers": 10145911, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tigre", + "speakers": 1094616, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tamil", + "speakers": 85616159, + "family": "Dravidian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Syriac", + "speakers": 210659, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Albanian", + "speakers": 6791906, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sylheti", + "speakers": 8132550, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Serbian", + "speakers": 15602410, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sranan Tongo", + "speakers": 414507, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Serer", + "speakers": 1731004, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sirmauri", + "speakers": 464132, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Swati", + "speakers": 2212379, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Saho", + "speakers": 218923, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Southern Sotho", + "speakers": 6390567, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Saterland Frisian", + "speakers": 962, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sundanese", + "speakers": 32043120, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sukuma", + "speakers": 5094094, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Susu", + "speakers": 1378014, + "family": "Mande", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Swedish", + "speakers": 12932871, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Swahili", + "speakers": 171610296, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Comorian", + "speakers": 170720, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Swabian", + "speakers": 801597, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Shekhawati", + "speakers": 3713052, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sangir", + "speakers": 245664, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lakota", + "speakers": 8316, + "family": "Siouan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lillooet", + "speakers": 528, + "family": "Salishan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lampung Api", + "speakers": 1842479, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Cherokee", + "speakers": 25613, + "family": "Iroquoian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Western Cham", + "speakers": 270832, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Eastern Cham", + "speakers": 87862, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Central Kurdish", + "speakers": 11086549, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Chilcotin", + "speakers": 867, + "family": "Athabaskan-Eyak-Tlingit", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Corsican", + "speakers": 162836, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Capiznon", + "speakers": 720595, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Cree", + "speakers": 9047, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Michif", + "speakers": 678, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Crimean Tatar", + "speakers": 245968, + "family": "Turkic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Plains Cree", + "speakers": 4146, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Northern East Cree", + "speakers": 377, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Seselwa Creole French", + "speakers": 94061, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Czech", + "speakers": 13045532, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kashubian", + "speakers": 49767, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Swampy Cree", + "speakers": 1809, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Church Slavic", + "speakers": 0, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Chuvash", + "speakers": 1842386, + "family": "Turkic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Chickasaw", + "speakers": 0, + "family": "Muskogean", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Chipewyan", + "speakers": 12816, + "family": "Athabaskan-Eyak-Tlingit", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Danish", + "speakers": 7072056, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Choctaw", + "speakers": 10977, + "family": "Muskogean", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bushi", + "speakers": 44620, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Buginese", + "speakers": 4298211, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bulu", + "speakers": 1276270, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bube", + "speakers": 66058, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Blin", + "speakers": 79056, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Medumba", + "speakers": 305195, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Jenaama Bozo", + "speakers": 166204, + "family": "Mande", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Catalan", + "speakers": 8679139, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Caddo", + "speakers": 0, + "family": "Caddoan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Atsam", + "speakers": 44946, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Chakma", + "speakers": 729137, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Chechen", + "speakers": 935365, + "family": "Nakh-Daghestanian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Cebuano", + "speakers": 26203440, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Chiga", + "speakers": 2335662, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Chamorro", + "speakers": 46325, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Chuukese", + "speakers": 30731, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mari", + "speakers": 524371, + "family": "Uralic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Welsh", + "speakers": 884910, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Dakota", + "speakers": 20832, + "family": "Siouan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bateri", + "speakers": 78843, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Efik", + "speakers": 2996392, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Greek", + "speakers": 12292242, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Esperanto", + "speakers": 301, + "family": "Artificial Language", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Central Yupik", + "speakers": 20956, + "family": "Eskimo-Aleut", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Estonian", + "speakers": 878449, + "family": "Uralic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Basque", + "speakers": 1088519, + "family": null, + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ewondo", + "speakers": 860095, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Extremaduran", + "speakers": 245077, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Persian", + "speakers": 84710459, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Fang", + "speakers": 426451, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "West Albay Bikol", + "speakers": 2511163, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Fula", + "speakers": 7788904, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Maasina Fulfulde", + "speakers": 1505612, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Finnish", + "speakers": 5736842, + "family": "Uralic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nobiin", + "speakers": 378161, + "family": "Nubian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Filipino", + "speakers": 67471096, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tornedalen Finnish", + "speakers": 56114, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Fijian", + "speakers": 365030, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Emilian", + "speakers": 31201, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ewe", + "speakers": 4690857, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Dargwa", + "speakers": 368477, + "family": "Nakh-Daghestanian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Embu", + "speakers": 802918, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Taita", + "speakers": 438929, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Deccan", + "speakers": 13128291, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "German", + "speakers": 136350226, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Slave", + "speakers": 2299, + "family": "Athabaskan-Eyak-Tlingit", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Dogrib", + "speakers": 2111, + "family": "Athabaskan-Eyak-Tlingit", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Zarma", + "speakers": 3871308, + "family": "Songhay", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Dan", + "speakers": 1099244, + "family": "Mande", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Dogri", + "speakers": 2652180, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lower Sorbian", + "speakers": 6974, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tomo Kan Dogon", + "speakers": 215087, + "family": "Dogon", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Central Dusun", + "speakers": 182852, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Dotyali", + "speakers": 758198, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Duala", + "speakers": 133176, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Divehi", + "speakers": 388044, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Jola-Fonyi", + "speakers": 409146, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Dyula", + "speakers": 6667328, + "family": "Mande", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Dzongkha", + "speakers": 370341, + "family": "Bookkeeping", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Buriat", + "speakers": 311788, + "family": "Mongolic-Khitan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Rinconada Bikol", + "speakers": 305707, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Fon", + "speakers": 3216150, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Algerian Arabic", + "speakers": 35667507, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Moroccan Arabic", + "speakers": 30938679, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Egyptian Arabic", + "speakers": 66639360, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Assamese", + "speakers": 17239170, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Asu", + "speakers": 702634, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Asturian", + "speakers": 650205, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Atikamekw", + "speakers": 6408, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Avaric", + "speakers": 552716, + "family": "Nakh-Daghestanian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Awadhi", + "speakers": 25862924, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Aymara", + "speakers": 2838620, + "family": "Aymaran", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Azerbaijani", + "speakers": 32446682, + "family": "Turkic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bashkir", + "speakers": 1842386, + "family": "Turkic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Baluchi", + "speakers": 8227887, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Balinese", + "speakers": 4806468, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bantawa", + "speakers": 454918, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bavarian", + "speakers": 22043627, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Basaa", + "speakers": 332940, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bamun", + "speakers": 332940, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Najdi Arabic", + "speakers": 1025205, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Araona", + "speakers": 105, + "family": "Pano-Tacanan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ghomala", + "speakers": 388430, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mapuche", + "speakers": 272802, + "family": "Araucanian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Abron", + "speakers": 1467010, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Achinese", + "speakers": 3738364, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Acoli", + "speakers": 1600361, + "family": "Nilotic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Adangme", + "speakers": 880206, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Adyghe", + "speakers": 444583, + "family": "Abkhaz-Adyge", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tunisian Arabic", + "speakers": 10549080, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Afrikaans", + "speakers": 9318845, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Aghem", + "speakers": 38843, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Akan", + "speakers": 11442678, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gheg Albanian", + "speakers": 1430250, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Southern Altai", + "speakers": 19841, + "family": "Turkic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Amharic", + "speakers": 35728475, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Amo", + "speakers": 18620, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Aragonese", + "speakers": 26008, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Obolo", + "speakers": 0, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Uab Meto", + "speakers": 720970, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "North Levantine Arabic", + "speakers": 39031474, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Batak Toba", + "speakers": 2456639, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Baoulé", + "speakers": 3022921, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Akoose", + "speakers": 149823, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Banjar", + "speakers": 4010288, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kom", + "speakers": 360685, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Buhid", + "speakers": 7970, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Siksiká", + "speakers": 4900, + "family": "Algic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Anii", + "speakers": 51507, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tai Dam", + "speakers": 681177, + "family": "Tai-Kadai", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bambara", + "speakers": 9385632, + "family": "Mande", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bomu", + "speakers": 168159, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tibetan", + "speakers": 3006697, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bishnupriya", + "speakers": 90174, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bakhtiari", + "speakers": 1188926, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Koro Wachi", + "speakers": 46718, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Breton", + "speakers": 563140, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Braj", + "speakers": 54370, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Brahui", + "speakers": 3035513, + "family": "Dravidian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bodo", + "speakers": 1856526, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bosnian", + "speakers": 7594468, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bassari", + "speakers": 15264, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Balanta-Ganja", + "speakers": 95992, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kanauji", + "speakers": 7426104, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Belarusian", + "speakers": 10064517, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bini", + "speakers": 1519599, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Beja", + "speakers": 2460326, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bemba", + "speakers": 5402246, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Betawi", + "speakers": 5607546, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bena", + "speakers": 995398, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bafut", + "speakers": 158146, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Badaga", + "speakers": 305001, + "family": "Dravidian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Balti", + "speakers": 502520, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bagheli", + "speakers": 654424, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bulgarian", + "speakers": 7878315, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Haryanvi", + "speakers": 15913080, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Western Balochi", + "speakers": 2037382, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Balkan Gagauz Turkish", + "speakers": 377280, + "family": "Turkic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bhili", + "speakers": 1591308, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bhilali", + "speakers": 1220003, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bhojpuri", + "speakers": 32934797, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bislama", + "speakers": 268500, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bikol", + "speakers": 3275430, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Faroese", + "speakers": 71351, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Cajun French", + "speakers": 27942, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lisu", + "speakers": 627309, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Komering", + "speakers": 854483, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Khasi", + "speakers": 1060872, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lü", + "speakers": 264864, + "family": "Tai-Kadai", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Khandesi", + "speakers": 1989135, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Koyra Chiini", + "speakers": 332408, + "family": "Songhay", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Khamti", + "speakers": 13527, + "family": "Tai-Kadai", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Khowar", + "speakers": 350252, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kikuyu", + "speakers": 9099743, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kirmanjki", + "speakers": 155833, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kuanyama", + "speakers": 920524, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Khmu", + "speakers": 431949, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kazakh", + "speakers": 13637392, + "family": "Turkic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kako", + "speakers": 149823, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kalaallisut", + "speakers": 55440, + "family": "Eskimo-Aleut", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kalenjin", + "speakers": 4068120, + "family": "Nilotic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Khmer", + "speakers": 15065030, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kimbundu", + "speakers": 8130575, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kannada", + "speakers": 49065330, + "family": "Dravidian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kaingang", + "speakers": 50812, + "family": "Nuclear-Macro-Je", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kongo", + "speakers": 1526700, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Korean", + "speakers": 78357046, + "family": "Koreanic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kumaoni", + "speakers": 2917398, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Javanese", + "speakers": 91180665, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Georgian", + "speakers": 3543646, + "family": "Kartvelian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kara-Kalpak", + "speakers": 489046, + "family": "Turkic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kabyle", + "speakers": 3351886, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kachin", + "speakers": 962032, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Jju", + "speakers": 449459, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kamba", + "speakers": 4068120, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Xaasongaxango", + "speakers": 195534, + "family": "Mande", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kabardian", + "speakers": 1070873, + "family": "Abkhaz-Adyge", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tyap", + "speakers": 199046, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kalanga", + "speakers": 770954, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Makonde", + "speakers": 1463820, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kuy", + "speakers": 421207, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kabuverdianu", + "speakers": 530762, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kenyang", + "speakers": 69362, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Koro", + "speakers": 63207, + "family": "Mande", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kachhi", + "speakers": 994568, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Mankanya", + "speakers": 83151, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Komi-Permyak", + "speakers": 63775, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Jumli", + "speakers": 970493, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Wadiyara Koli", + "speakers": 256851, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kyrgyz", + "speakers": 3338267, + "family": "Turkic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Latin", + "speakers": 820, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ladino", + "speakers": 112781, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Langi", + "speakers": 509409, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Western Panjabi", + "speakers": 93433552, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lango (Uganda)", + "speakers": 1643614, + "family": "Nilotic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Luxembourgish", + "speakers": 421015, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lak", + "speakers": 110543, + "family": "Nakh-Daghestanian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Tolaki", + "speakers": 347134, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Western Lawa", + "speakers": 87751, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lepcha", + "speakers": 79743, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lezghian", + "speakers": 255100, + "family": "Nakh-Daghestanian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ganda", + "speakers": 5622890, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Limburgish", + "speakers": 950422, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Limbu", + "speakers": 368085, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ligurian", + "speakers": 536663, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Abkhazian", + "speakers": 91953, + "family": "Abkhaz-Adyge", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kuvi", + "speakers": 38457, + "family": "Dravidian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Northern Khmer", + "speakers": 1172616, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Konkani", + "speakers": 4906533, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kwakʼwala", + "speakers": 377, + "family": "Wakashan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kosraean", + "speakers": 7990, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kpelle", + "speakers": 1186303, + "family": "Mande", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Karachay-Balkar", + "speakers": 240927, + "family": "Turkic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Krio", + "speakers": 6293684, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kinaray-a", + "speakers": 425806, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Karelian", + "speakers": 116212, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kurukh", + "speakers": 2519571, + "family": "Dravidian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kashmiri", + "speakers": 5598085, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Shambala", + "speakers": 995398, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Bafia", + "speakers": 88784, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Colognian", + "speakers": 240479, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kurdish", + "speakers": 6866757, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kumyk", + "speakers": 283444, + "family": "Turkic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Komi", + "speakers": 255100, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kerinci", + "speakers": 373836, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Parkari Koli", + "speakers": 373602, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Cornish", + "speakers": 1973, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Jutish", + "speakers": 0, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Machame", + "speakers": 433291, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Arpitan", + "speakers": 63777, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Kachi Koli", + "speakers": 256851, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Galician", + "speakers": 3515530, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gilaki", + "speakers": 3906472, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Guarani", + "speakers": 5827107, + "family": "Tupian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Goan Konkani", + "speakers": 4243488, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gondi", + "speakers": 3182616, + "family": "Dravidian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gorontalo", + "speakers": 1094807, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gronings", + "speakers": 622094, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Garo", + "speakers": 821563, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Swiss German", + "speakers": 7956952, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gujarati", + "speakers": 61721799, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Guajajára", + "speakers": 17784, + "family": "Tupian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Wayuu", + "speakers": 132529, + "family": "Arawakan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Frafra", + "speakers": 1026907, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gusii", + "speakers": 2622867, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Manx", + "speakers": 1719, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gurung", + "speakers": 87951, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gwichʼin", + "speakers": 302, + "family": "Athabaskan-Eyak-Tlingit", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gujari", + "speakers": 467002, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gilbertese", + "speakers": 67078, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hakka Chinese", + "speakers": 32062460, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Geez", + "speakers": 0, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Northern Frisian", + "speakers": 9619, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Eastern Frisian", + "speakers": 2004, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "East Futuna", + "speakers": 4756, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Central-Eastern Niger Fulfulde", + "speakers": 1594068, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Friulian", + "speakers": 37442, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Nigerian Fulfulde", + "speakers": 14339876, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Fur", + "speakers": 1230163, + "family": "Furan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Western Frisian", + "speakers": 743057, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Irish", + "speakers": 1237487, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ga", + "speakers": 821526, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gagauz", + "speakers": 111028, + "family": "Turkic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gan Chinese", + "speakers": 23698340, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Gayo", + "speakers": 320431, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Garhwali", + "speakers": 3580443, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Zoroastrian Dari", + "speakers": 7983, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Guianese Creole French", + "speakers": 51872, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Scottish Gaelic", + "speakers": 72337, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hausa", + "speakers": 40411882, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hawaiian", + "speakers": 29605, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ngomba", + "speakers": 94333, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Interlingua", + "speakers": 136, + "family": "Artificial Language", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ibibio", + "speakers": 2996392, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Indonesian", + "speakers": 171207687, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Interlingue", + "speakers": 1, + "family": "Artificial Language", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ifè", + "speakers": 111910, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Igbo", + "speakers": 27823640, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Sichuan Yi", + "speakers": 8364120, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Inupiaq", + "speakers": 7983, + "family": "Eskimo-Aleut", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Iloko", + "speakers": 10481376, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ingush", + "speakers": 226755, + "family": "Nakh-Daghestanian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ido", + "speakers": 0, + "family": "Artificial Language", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Icelandic", + "speakers": 350734, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Italian", + "speakers": 70247060, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Inuktitut", + "speakers": 90466, + "family": "Eskimo-Aleut", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ingrian", + "speakers": 142, + "family": "Uralic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Japanese", + "speakers": 119729026, + "family": "Japonic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Jamaican Creole English", + "speakers": 2668142, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Lojban", + "speakers": 0, + "family": "Artificial Language", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Iban", + "speakers": 816302, + "family": "Bookkeeping", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Herero", + "speakers": 239336, + "family": "Atlantic-Congo", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hazaragi", + "speakers": 2161984, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Armenian", + "speakers": 5317273, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hebrew", + "speakers": 8675480, + "family": "Afro-Asiatic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Fiji Hindi", + "speakers": 383749, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hiligaynon", + "speakers": 9171204, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Southern Hindko", + "speakers": 957354, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Chhattisgarhi", + "speakers": 14586990, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hmong Njua", + "speakers": 781687, + "family": "Hmong-Mien", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hanunoo", + "speakers": 17469, + "family": "Austronesian", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Northern Hindko", + "speakers": 3969517, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hiri Motu", + "speakers": 152449, + "family": "Pidgin", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Ho", + "speakers": 1312829, + "family": "Austroasiatic", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hadothi", + "speakers": 1087394, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Croatian", + "speakers": 6813164, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Upper Sorbian", + "speakers": 12826, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Xiang Chinese", + "speakers": 40426580, + "family": "Sino-Tibetan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Haitian Creole", + "speakers": 8964918, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Hungarian", + "speakers": 12443430, + "family": "Uralic", + "average": 0.0, + "in_benchmark": true, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Halkomelem", + "speakers": 716, + "family": "Salishan", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + }, + { + "language_name": "Zaza", + "speakers": 1148245, + "family": "Indo-European", + "average": 0.0, + "in_benchmark": false, + "NaN": 0.0, + "classification_accuracy": 0.0, + "language_modeling_chrf": 0.0, + "translation_bleu": 0.0, + "translation_chrf": 0.0 + } ] } \ No newline at end of file