training_date: "2026-03-04T13:41:09Z" max_samples: 15000 models: ar/cp720: language: ar encoding: cp720 samples_used: 25000 bigram_entries: 844 source: culturax ar/cp864: language: ar encoding: cp864 samples_used: 25000 bigram_entries: 42 source: culturax ar/iso-8859-6: language: ar encoding: iso-8859-6 samples_used: 25000 bigram_entries: 844 source: culturax ar/utf-8: language: ar encoding: utf-8 samples_used: 25000 bigram_entries: 204 source: culturax ar/windows-1256: language: ar encoding: windows-1256 samples_used: 25000 bigram_entries: 847 source: culturax be/cp855: language: be encoding: cp855 samples_used: 25000 bigram_entries: 1198 source: culturax be/cp866: language: be encoding: cp866 samples_used: 25000 bigram_entries: 1158 source: culturax be/iso-8859-5: language: be encoding: iso-8859-5 samples_used: 25000 bigram_entries: 1174 source: culturax be/mac-cyrillic: language: be encoding: mac-cyrillic samples_used: 25000 bigram_entries: 1198 source: culturax be/utf-8: language: be encoding: utf-8 samples_used: 25000 bigram_entries: 235 source: culturax be/windows-1251: language: be encoding: windows-1251 samples_used: 25000 bigram_entries: 1197 source: culturax bg/cp855: language: bg encoding: cp855 samples_used: 25000 bigram_entries: 875 source: culturax bg/cp866: language: bg encoding: cp866 samples_used: 25000 bigram_entries: 877 source: culturax bg/iso-8859-5: language: bg encoding: iso-8859-5 samples_used: 25000 bigram_entries: 876 source: culturax bg/mac-cyrillic: language: bg encoding: mac-cyrillic samples_used: 25000 bigram_entries: 876 source: culturax bg/utf-8: language: bg encoding: utf-8 samples_used: 25000 bigram_entries: 229 source: culturax bg/windows-1251: language: bg encoding: windows-1251 samples_used: 25000 bigram_entries: 875 source: culturax br/iso-8859-14: language: br encoding: iso-8859-14 samples_used: 25000 bigram_entries: 861 source: culturax br/utf-8: language: br encoding: utf-8 samples_used: 25000 bigram_entries: 883 source: culturax cs/cp852: language: cs encoding: cp852 samples_used: 25000 bigram_entries: 1355 source: culturax cs/iso-8859-2: language: cs encoding: iso-8859-2 samples_used: 25000 bigram_entries: 1353 source: culturax cs/mac-latin2: language: cs encoding: mac-latin2 samples_used: 25000 bigram_entries: 1355 source: culturax cs/utf-8: language: cs encoding: utf-8 samples_used: 25000 bigram_entries: 1097 source: culturax cs/windows-1250: language: cs encoding: windows-1250 samples_used: 25000 bigram_entries: 1355 source: culturax cy/iso-8859-14: language: cy encoding: iso-8859-14 samples_used: 25000 bigram_entries: 764 source: culturax cy/utf-8: language: cy encoding: utf-8 samples_used: 25000 bigram_entries: 777 source: culturax da/cp1140: language: da encoding: cp1140 samples_used: 25000 bigram_entries: 787 source: culturax da/cp437: language: da encoding: cp437 samples_used: 25000 bigram_entries: 766 source: culturax da/cp500: language: da encoding: cp500 samples_used: 25000 bigram_entries: 787 source: culturax da/cp850: language: da encoding: cp850 samples_used: 25000 bigram_entries: 788 source: culturax da/cp858: language: da encoding: cp858 samples_used: 25000 bigram_entries: 787 source: culturax da/cp865: language: da encoding: cp865 samples_used: 25000 bigram_entries: 788 source: culturax da/hp-roman8: language: da encoding: hp-roman8 samples_used: 25000 bigram_entries: 788 source: culturax da/iso-8859-1: language: da encoding: iso-8859-1 samples_used: 25000 bigram_entries: 787 source: culturax da/iso-8859-15: language: da encoding: iso-8859-15 samples_used: 25000 bigram_entries: 788 source: culturax da/mac-roman: language: da encoding: mac-roman samples_used: 25000 bigram_entries: 787 source: culturax da/utf-8: language: da encoding: utf-8 samples_used: 25000 bigram_entries: 773 source: culturax da/windows-1252: language: da encoding: windows-1252 samples_used: 25000 bigram_entries: 787 source: culturax de/cp1140: language: de encoding: cp1140 samples_used: 25000 bigram_entries: 903 source: culturax de/cp273: language: de encoding: cp273 samples_used: 25000 bigram_entries: 904 source: culturax de/cp437: language: de encoding: cp437 samples_used: 25000 bigram_entries: 904 source: culturax de/cp500: language: de encoding: cp500 samples_used: 25000 bigram_entries: 904 source: culturax de/cp850: language: de encoding: cp850 samples_used: 25000 bigram_entries: 904 source: culturax de/cp858: language: de encoding: cp858 samples_used: 25000 bigram_entries: 903 source: culturax de/hp-roman8: language: de encoding: hp-roman8 samples_used: 25000 bigram_entries: 904 source: culturax de/iso-8859-1: language: de encoding: iso-8859-1 samples_used: 25000 bigram_entries: 904 source: culturax de/iso-8859-15: language: de encoding: iso-8859-15 samples_used: 25000 bigram_entries: 903 source: culturax de/mac-roman: language: de encoding: mac-roman samples_used: 25000 bigram_entries: 903 source: culturax de/utf-8: language: de encoding: utf-8 samples_used: 25000 bigram_entries: 900 source: culturax de/windows-1252: language: de encoding: windows-1252 samples_used: 25000 bigram_entries: 903 source: culturax el/cp737: language: el encoding: cp737 samples_used: 25000 bigram_entries: 1313 source: culturax el/cp869: language: el encoding: cp869 samples_used: 25000 bigram_entries: 1324 source: culturax el/cp875: language: el encoding: cp875 samples_used: 25000 bigram_entries: 1325 source: culturax el/iso-8859-7: language: el encoding: iso-8859-7 samples_used: 25000 bigram_entries: 1323 source: culturax el/mac-greek: language: el encoding: mac-greek samples_used: 25000 bigram_entries: 1323 source: culturax el/utf-8: language: el encoding: utf-8 samples_used: 25000 bigram_entries: 293 source: culturax el/windows-1253: language: el encoding: windows-1253 samples_used: 25000 bigram_entries: 1325 source: culturax en/cp1140: language: en encoding: cp1140 samples_used: 15000 bigram_entries: 795 source: culturax en/cp437: language: en encoding: cp437 samples_used: 15000 bigram_entries: 796 source: culturax en/cp500: language: en encoding: cp500 samples_used: 15000 bigram_entries: 795 source: culturax en/cp850: language: en encoding: cp850 samples_used: 15000 bigram_entries: 795 source: culturax en/cp858: language: en encoding: cp858 samples_used: 15000 bigram_entries: 795 source: culturax en/hp-roman8: language: en encoding: hp-roman8 samples_used: 15000 bigram_entries: 796 source: culturax en/iso-8859-1: language: en encoding: iso-8859-1 samples_used: 15000 bigram_entries: 795 source: culturax en/iso-8859-15: language: en encoding: iso-8859-15 samples_used: 15000 bigram_entries: 795 source: culturax en/mac-roman: language: en encoding: mac-roman samples_used: 15000 bigram_entries: 795 source: culturax en/utf-8: language: en encoding: utf-8 samples_used: 15000 bigram_entries: 796 source: culturax en/windows-1252: language: en encoding: windows-1252 samples_used: 15000 bigram_entries: 795 source: culturax eo/iso-8859-3: language: eo encoding: iso-8859-3 samples_used: 25000 bigram_entries: 1025 source: culturax eo/utf-8: language: eo encoding: utf-8 samples_used: 25000 bigram_entries: 1036 source: culturax es/cp1140: language: es encoding: cp1140 samples_used: 25000 bigram_entries: 801 source: culturax es/cp437: language: es encoding: cp437 samples_used: 25000 bigram_entries: 801 source: culturax es/cp500: language: es encoding: cp500 samples_used: 25000 bigram_entries: 801 source: culturax es/cp850: language: es encoding: cp850 samples_used: 25000 bigram_entries: 801 source: culturax es/cp858: language: es encoding: cp858 samples_used: 25000 bigram_entries: 801 source: culturax es/hp-roman8: language: es encoding: hp-roman8 samples_used: 25000 bigram_entries: 801 source: culturax es/iso-8859-1: language: es encoding: iso-8859-1 samples_used: 25000 bigram_entries: 801 source: culturax es/iso-8859-15: language: es encoding: iso-8859-15 samples_used: 25000 bigram_entries: 801 source: culturax es/mac-roman: language: es encoding: mac-roman samples_used: 25000 bigram_entries: 801 source: culturax es/utf-8: language: es encoding: utf-8 samples_used: 25000 bigram_entries: 777 source: culturax es/windows-1252: language: es encoding: windows-1252 samples_used: 25000 bigram_entries: 801 source: culturax et/cp775: language: et encoding: cp775 samples_used: 25000 bigram_entries: 878 source: culturax et/iso-8859-13: language: et encoding: iso-8859-13 samples_used: 25000 bigram_entries: 878 source: culturax et/iso-8859-4: language: et encoding: iso-8859-4 samples_used: 25000 bigram_entries: 877 source: culturax et/utf-8: language: et encoding: utf-8 samples_used: 25000 bigram_entries: 855 source: culturax et/windows-1257: language: et encoding: windows-1257 samples_used: 25000 bigram_entries: 878 source: culturax fa/cp720: language: fa encoding: cp720 samples_used: 25000 bigram_entries: 741 source: culturax fa/iso-8859-6: language: fa encoding: iso-8859-6 samples_used: 25000 bigram_entries: 740 source: culturax fa/utf-8: language: fa encoding: utf-8 samples_used: 25000 bigram_entries: 224 source: culturax fa/windows-1256: language: fa encoding: windows-1256 samples_used: 25000 bigram_entries: 882 source: culturax fi/cp1140: language: fi encoding: cp1140 samples_used: 25000 bigram_entries: 722 source: culturax fi/cp437: language: fi encoding: cp437 samples_used: 25000 bigram_entries: 723 source: culturax fi/cp500: language: fi encoding: cp500 samples_used: 25000 bigram_entries: 723 source: culturax fi/cp850: language: fi encoding: cp850 samples_used: 25000 bigram_entries: 723 source: culturax fi/cp858: language: fi encoding: cp858 samples_used: 25000 bigram_entries: 722 source: culturax fi/hp-roman8: language: fi encoding: hp-roman8 samples_used: 25000 bigram_entries: 723 source: culturax fi/iso-8859-1: language: fi encoding: iso-8859-1 samples_used: 25000 bigram_entries: 723 source: culturax fi/iso-8859-10: language: fi encoding: iso-8859-10 samples_used: 25000 bigram_entries: 723 source: culturax fi/iso-8859-15: language: fi encoding: iso-8859-15 samples_used: 25000 bigram_entries: 722 source: culturax fi/mac-roman: language: fi encoding: mac-roman samples_used: 25000 bigram_entries: 722 source: culturax fi/utf-8: language: fi encoding: utf-8 samples_used: 25000 bigram_entries: 692 source: culturax fi/windows-1252: language: fi encoding: windows-1252 samples_used: 25000 bigram_entries: 722 source: culturax fr/cp1140: language: fr encoding: cp1140 samples_used: 25000 bigram_entries: 699 source: culturax fr/cp437: language: fr encoding: cp437 samples_used: 25000 bigram_entries: 700 source: culturax fr/cp500: language: fr encoding: cp500 samples_used: 25000 bigram_entries: 700 source: culturax fr/cp850: language: fr encoding: cp850 samples_used: 25000 bigram_entries: 700 source: culturax fr/cp858: language: fr encoding: cp858 samples_used: 25000 bigram_entries: 699 source: culturax fr/cp863: language: fr encoding: cp863 samples_used: 25000 bigram_entries: 700 source: culturax fr/hp-roman8: language: fr encoding: hp-roman8 samples_used: 25000 bigram_entries: 700 source: culturax fr/iso-8859-1: language: fr encoding: iso-8859-1 samples_used: 25000 bigram_entries: 700 source: culturax fr/iso-8859-15: language: fr encoding: iso-8859-15 samples_used: 25000 bigram_entries: 700 source: culturax fr/mac-roman: language: fr encoding: mac-roman samples_used: 25000 bigram_entries: 700 source: culturax fr/utf-8: language: fr encoding: utf-8 samples_used: 25000 bigram_entries: 699 source: culturax fr/windows-1252: language: fr encoding: windows-1252 samples_used: 25000 bigram_entries: 700 source: culturax ga/iso-8859-14: language: ga encoding: iso-8859-14 samples_used: 25000 bigram_entries: 703 source: culturax ga/utf-8: language: ga encoding: utf-8 samples_used: 25000 bigram_entries: 659 source: culturax gd/iso-8859-14: language: gd encoding: iso-8859-14 samples_used: 8408 bigram_entries: 540 source: culturax gd/utf-8: language: gd encoding: utf-8 samples_used: 8408 bigram_entries: 515 source: culturax he/cp424: language: he encoding: cp424 samples_used: 25000 bigram_entries: 979 source: culturax he/cp856: language: he encoding: cp856 samples_used: 25000 bigram_entries: 979 source: culturax he/cp862: language: he encoding: cp862 samples_used: 25000 bigram_entries: 980 source: culturax he/iso-8859-8: language: he encoding: iso-8859-8 samples_used: 25000 bigram_entries: 979 source: culturax he/utf-8: language: he encoding: utf-8 samples_used: 25000 bigram_entries: 154 source: culturax he/windows-1255: language: he encoding: windows-1255 samples_used: 25000 bigram_entries: 1099 source: culturax hr/cp852: language: hr encoding: cp852 samples_used: 25000 bigram_entries: 676 source: culturax hr/iso-8859-16: language: hr encoding: iso-8859-16 samples_used: 25000 bigram_entries: 677 source: culturax hr/iso-8859-2: language: hr encoding: iso-8859-2 samples_used: 25000 bigram_entries: 676 source: culturax hr/mac-latin2: language: hr encoding: mac-latin2 samples_used: 25000 bigram_entries: 674 source: culturax hr/utf-8: language: hr encoding: utf-8 samples_used: 25000 bigram_entries: 665 source: culturax hr/windows-1250: language: hr encoding: windows-1250 samples_used: 25000 bigram_entries: 677 source: culturax hu/cp852: language: hu encoding: cp852 samples_used: 25000 bigram_entries: 1243 source: culturax hu/iso-8859-16: language: hu encoding: iso-8859-16 samples_used: 25000 bigram_entries: 1243 source: culturax hu/iso-8859-2: language: hu encoding: iso-8859-2 samples_used: 25000 bigram_entries: 1243 source: culturax hu/mac-latin2: language: hu encoding: mac-latin2 samples_used: 25000 bigram_entries: 1243 source: culturax hu/utf-8: language: hu encoding: utf-8 samples_used: 25000 bigram_entries: 965 source: culturax hu/windows-1250: language: hu encoding: windows-1250 samples_used: 25000 bigram_entries: 1243 source: culturax id/cp1140: language: id encoding: cp1140 samples_used: 25000 bigram_entries: 536 source: culturax id/cp500: language: id encoding: cp500 samples_used: 25000 bigram_entries: 536 source: culturax id/cp850: language: id encoding: cp850 samples_used: 25000 bigram_entries: 536 source: culturax id/cp858: language: id encoding: cp858 samples_used: 25000 bigram_entries: 536 source: culturax id/hp-roman8: language: id encoding: hp-roman8 samples_used: 25000 bigram_entries: 536 source: culturax id/iso-8859-1: language: id encoding: iso-8859-1 samples_used: 25000 bigram_entries: 536 source: culturax id/iso-8859-15: language: id encoding: iso-8859-15 samples_used: 25000 bigram_entries: 536 source: culturax id/mac-roman: language: id encoding: mac-roman samples_used: 25000 bigram_entries: 536 source: culturax id/utf-8: language: id encoding: utf-8 samples_used: 25000 bigram_entries: 536 source: culturax id/windows-1252: language: id encoding: windows-1252 samples_used: 25000 bigram_entries: 536 source: culturax is/cp1140: language: is encoding: cp1140 samples_used: 25000 bigram_entries: 1034 source: culturax is/cp500: language: is encoding: cp500 samples_used: 25000 bigram_entries: 1034 source: culturax is/cp850: language: is encoding: cp850 samples_used: 25000 bigram_entries: 1034 source: culturax is/cp858: language: is encoding: cp858 samples_used: 25000 bigram_entries: 1034 source: culturax is/cp861: language: is encoding: cp861 samples_used: 25000 bigram_entries: 1016 source: culturax is/hp-roman8: language: is encoding: hp-roman8 samples_used: 25000 bigram_entries: 1016 source: culturax is/iso-8859-1: language: is encoding: iso-8859-1 samples_used: 25000 bigram_entries: 1034 source: culturax is/iso-8859-10: language: is encoding: iso-8859-10 samples_used: 25000 bigram_entries: 1035 source: culturax is/iso-8859-15: language: is encoding: iso-8859-15 samples_used: 25000 bigram_entries: 1034 source: culturax is/mac-iceland: language: is encoding: mac-iceland samples_used: 25000 bigram_entries: 1016 source: culturax is/mac-roman: language: is encoding: mac-roman samples_used: 25000 bigram_entries: 906 source: culturax is/utf-8: language: is encoding: utf-8 samples_used: 25000 bigram_entries: 828 source: culturax is/windows-1252: language: is encoding: windows-1252 samples_used: 25000 bigram_entries: 1034 source: culturax it/cp1140: language: it encoding: cp1140 samples_used: 25000 bigram_entries: 661 source: culturax it/cp437: language: it encoding: cp437 samples_used: 25000 bigram_entries: 661 source: culturax it/cp500: language: it encoding: cp500 samples_used: 25000 bigram_entries: 662 source: culturax it/cp850: language: it encoding: cp850 samples_used: 25000 bigram_entries: 662 source: culturax it/cp858: language: it encoding: cp858 samples_used: 25000 bigram_entries: 661 source: culturax it/hp-roman8: language: it encoding: hp-roman8 samples_used: 25000 bigram_entries: 662 source: culturax it/iso-8859-1: language: it encoding: iso-8859-1 samples_used: 25000 bigram_entries: 662 source: culturax it/iso-8859-15: language: it encoding: iso-8859-15 samples_used: 25000 bigram_entries: 661 source: culturax it/mac-roman: language: it encoding: mac-roman samples_used: 25000 bigram_entries: 661 source: culturax it/utf-8: language: it encoding: utf-8 samples_used: 25000 bigram_entries: 670 source: culturax it/windows-1252: language: it encoding: windows-1252 samples_used: 25000 bigram_entries: 661 source: culturax ja/cp932: language: ja encoding: cp932 samples_used: 25000 bigram_entries: 3515 source: culturax ja/euc-jis-2004: language: ja encoding: euc-jis-2004 samples_used: 25000 bigram_entries: 2793 source: culturax ja/iso2022-jp-2: language: ja encoding: iso2022-jp-2 samples_used: 25000 bigram_entries: 2393 source: culturax ja/iso2022-jp-2004: language: ja encoding: iso2022-jp-2004 samples_used: 25000 bigram_entries: 2395 source: culturax ja/iso2022-jp-ext: language: ja encoding: iso2022-jp-ext samples_used: 25000 bigram_entries: 2399 source: culturax ja/shift_jis_2004: language: ja encoding: shift_jis_2004 samples_used: 25000 bigram_entries: 3515 source: culturax ja/utf-8: language: ja encoding: utf-8 samples_used: 25000 bigram_entries: 627 source: culturax kk/kz-1048: language: kk encoding: kz-1048 samples_used: 25000 bigram_entries: 1228 source: culturax kk/ptcp154: language: kk encoding: ptcp154 samples_used: 25000 bigram_entries: 1213 source: culturax kk/utf-8: language: kk encoding: utf-8 samples_used: 25000 bigram_entries: 291 source: culturax ko/cp949: language: ko encoding: cp949 samples_used: 25000 bigram_entries: 2905 source: culturax ko/euc-kr: language: ko encoding: euc-kr samples_used: 25000 bigram_entries: 2905 source: culturax ko/iso-2022-kr: language: ko encoding: iso-2022-kr samples_used: 25000 bigram_entries: 814 source: culturax ko/johab: language: ko encoding: johab samples_used: 25000 bigram_entries: 2075 source: culturax ko/utf-8: language: ko encoding: utf-8 samples_used: 25000 bigram_entries: 926 source: culturax lt/cp775: language: lt encoding: cp775 samples_used: 25000 bigram_entries: 943 source: culturax lt/iso-8859-13: language: lt encoding: iso-8859-13 samples_used: 25000 bigram_entries: 943 source: culturax lt/iso-8859-4: language: lt encoding: iso-8859-4 samples_used: 25000 bigram_entries: 943 source: culturax lt/utf-8: language: lt encoding: utf-8 samples_used: 25000 bigram_entries: 894 source: culturax lt/windows-1257: language: lt encoding: windows-1257 samples_used: 25000 bigram_entries: 943 source: culturax lv/cp775: language: lv encoding: cp775 samples_used: 25000 bigram_entries: 908 source: culturax lv/iso-8859-13: language: lv encoding: iso-8859-13 samples_used: 25000 bigram_entries: 908 source: culturax lv/iso-8859-4: language: lv encoding: iso-8859-4 samples_used: 25000 bigram_entries: 905 source: culturax lv/utf-8: language: lv encoding: utf-8 samples_used: 25000 bigram_entries: 806 source: culturax lv/windows-1257: language: lv encoding: windows-1257 samples_used: 25000 bigram_entries: 908 source: culturax mk/cp855: language: mk encoding: cp855 samples_used: 25000 bigram_entries: 699 source: culturax mk/cp866: language: mk encoding: cp866 samples_used: 25000 bigram_entries: 650 source: culturax mk/iso-8859-5: language: mk encoding: iso-8859-5 samples_used: 25000 bigram_entries: 699 source: culturax mk/mac-cyrillic: language: mk encoding: mac-cyrillic samples_used: 25000 bigram_entries: 699 source: culturax mk/utf-8: language: mk encoding: utf-8 samples_used: 25000 bigram_entries: 184 source: culturax mk/windows-1251: language: mk encoding: windows-1251 samples_used: 25000 bigram_entries: 699 source: culturax ms/cp1140: language: ms encoding: cp1140 samples_used: 25000 bigram_entries: 673 source: culturax ms/cp500: language: ms encoding: cp500 samples_used: 25000 bigram_entries: 673 source: culturax ms/cp850: language: ms encoding: cp850 samples_used: 25000 bigram_entries: 673 source: culturax ms/cp858: language: ms encoding: cp858 samples_used: 25000 bigram_entries: 673 source: culturax ms/hp-roman8: language: ms encoding: hp-roman8 samples_used: 25000 bigram_entries: 673 source: culturax ms/iso-8859-1: language: ms encoding: iso-8859-1 samples_used: 25000 bigram_entries: 673 source: culturax ms/iso-8859-15: language: ms encoding: iso-8859-15 samples_used: 25000 bigram_entries: 673 source: culturax ms/mac-roman: language: ms encoding: mac-roman samples_used: 25000 bigram_entries: 673 source: culturax ms/utf-8: language: ms encoding: utf-8 samples_used: 25000 bigram_entries: 680 source: culturax ms/windows-1252: language: ms encoding: windows-1252 samples_used: 25000 bigram_entries: 673 source: culturax mt/iso-8859-3: language: mt encoding: iso-8859-3 samples_used: 25000 bigram_entries: 972 source: culturax mt/utf-8: language: mt encoding: utf-8 samples_used: 25000 bigram_entries: 962 source: culturax nl/cp1140: language: nl encoding: cp1140 samples_used: 25000 bigram_entries: 694 source: culturax nl/cp437: language: nl encoding: cp437 samples_used: 25000 bigram_entries: 694 source: culturax nl/cp500: language: nl encoding: cp500 samples_used: 25000 bigram_entries: 694 source: culturax nl/cp850: language: nl encoding: cp850 samples_used: 25000 bigram_entries: 694 source: culturax nl/cp858: language: nl encoding: cp858 samples_used: 25000 bigram_entries: 694 source: culturax nl/hp-roman8: language: nl encoding: hp-roman8 samples_used: 25000 bigram_entries: 694 source: culturax nl/iso-8859-1: language: nl encoding: iso-8859-1 samples_used: 25000 bigram_entries: 694 source: culturax nl/iso-8859-15: language: nl encoding: iso-8859-15 samples_used: 25000 bigram_entries: 694 source: culturax nl/mac-roman: language: nl encoding: mac-roman samples_used: 25000 bigram_entries: 694 source: culturax nl/utf-8: language: nl encoding: utf-8 samples_used: 25000 bigram_entries: 700 source: culturax nl/windows-1252: language: nl encoding: windows-1252 samples_used: 25000 bigram_entries: 694 source: culturax no/cp1140: language: no encoding: cp1140 samples_used: 25000 bigram_entries: 802 source: culturax no/cp500: language: no encoding: cp500 samples_used: 25000 bigram_entries: 802 source: culturax no/cp850: language: no encoding: cp850 samples_used: 25000 bigram_entries: 802 source: culturax no/cp858: language: no encoding: cp858 samples_used: 25000 bigram_entries: 802 source: culturax no/cp865: language: no encoding: cp865 samples_used: 25000 bigram_entries: 803 source: culturax no/hp-roman8: language: no encoding: hp-roman8 samples_used: 25000 bigram_entries: 802 source: culturax no/iso-8859-1: language: no encoding: iso-8859-1 samples_used: 25000 bigram_entries: 802 source: culturax no/iso-8859-15: language: no encoding: iso-8859-15 samples_used: 25000 bigram_entries: 802 source: culturax no/mac-roman: language: no encoding: mac-roman samples_used: 25000 bigram_entries: 802 source: culturax no/utf-8: language: no encoding: utf-8 samples_used: 25000 bigram_entries: 798 source: culturax no/windows-1252: language: no encoding: windows-1252 samples_used: 25000 bigram_entries: 802 source: culturax pl/cp852: language: pl encoding: cp852 samples_used: 25000 bigram_entries: 1107 source: culturax pl/iso-8859-16: language: pl encoding: iso-8859-16 samples_used: 25000 bigram_entries: 1106 source: culturax pl/iso-8859-2: language: pl encoding: iso-8859-2 samples_used: 25000 bigram_entries: 1106 source: culturax pl/mac-latin2: language: pl encoding: mac-latin2 samples_used: 25000 bigram_entries: 1106 source: culturax pl/utf-8: language: pl encoding: utf-8 samples_used: 25000 bigram_entries: 1077 source: culturax pl/windows-1250: language: pl encoding: windows-1250 samples_used: 25000 bigram_entries: 1106 source: culturax pt/cp1140: language: pt encoding: cp1140 samples_used: 25000 bigram_entries: 828 source: culturax pt/cp437: language: pt encoding: cp437 samples_used: 25000 bigram_entries: 812 source: culturax pt/cp500: language: pt encoding: cp500 samples_used: 25000 bigram_entries: 828 source: culturax pt/cp850: language: pt encoding: cp850 samples_used: 25000 bigram_entries: 828 source: culturax pt/cp858: language: pt encoding: cp858 samples_used: 25000 bigram_entries: 828 source: culturax pt/cp860: language: pt encoding: cp860 samples_used: 25000 bigram_entries: 829 source: culturax pt/hp-roman8: language: pt encoding: hp-roman8 samples_used: 25000 bigram_entries: 829 source: culturax pt/iso-8859-1: language: pt encoding: iso-8859-1 samples_used: 25000 bigram_entries: 828 source: culturax pt/iso-8859-15: language: pt encoding: iso-8859-15 samples_used: 25000 bigram_entries: 828 source: culturax pt/mac-roman: language: pt encoding: mac-roman samples_used: 25000 bigram_entries: 828 source: culturax pt/utf-8: language: pt encoding: utf-8 samples_used: 25000 bigram_entries: 792 source: culturax pt/windows-1252: language: pt encoding: windows-1252 samples_used: 25000 bigram_entries: 828 source: culturax ro/iso-8859-16: language: ro encoding: iso-8859-16 samples_used: 25000 bigram_entries: 707 source: culturax ro/iso-8859-2: language: ro encoding: iso-8859-2 samples_used: 25000 bigram_entries: 714 source: culturax ro/utf-8: language: ro encoding: utf-8 samples_used: 25000 bigram_entries: 717 source: culturax ro/windows-1250: language: ro encoding: windows-1250 samples_used: 25000 bigram_entries: 713 source: culturax ru/cp855: language: ru encoding: cp855 samples_used: 25000 bigram_entries: 1441 source: culturax ru/cp866: language: ru encoding: cp866 samples_used: 25000 bigram_entries: 1415 source: culturax ru/iso-8859-5: language: ru encoding: iso-8859-5 samples_used: 25000 bigram_entries: 1414 source: culturax ru/koi8-r: language: ru encoding: koi8-r samples_used: 25000 bigram_entries: 1411 source: culturax ru/mac-cyrillic: language: ru encoding: mac-cyrillic samples_used: 25000 bigram_entries: 1441 source: culturax ru/utf-8: language: ru encoding: utf-8 samples_used: 25000 bigram_entries: 259 source: culturax ru/windows-1251: language: ru encoding: windows-1251 samples_used: 25000 bigram_entries: 1441 source: culturax sk/cp852: language: sk encoding: cp852 samples_used: 25000 bigram_entries: 1257 source: culturax sk/iso-8859-16: language: sk encoding: iso-8859-16 samples_used: 25000 bigram_entries: 1148 source: culturax sk/iso-8859-2: language: sk encoding: iso-8859-2 samples_used: 25000 bigram_entries: 1258 source: culturax sk/mac-latin2: language: sk encoding: mac-latin2 samples_used: 25000 bigram_entries: 1257 source: culturax sk/utf-8: language: sk encoding: utf-8 samples_used: 25000 bigram_entries: 1165 source: culturax sk/windows-1250: language: sk encoding: windows-1250 samples_used: 25000 bigram_entries: 1259 source: culturax sl/cp852: language: sl encoding: cp852 samples_used: 25000 bigram_entries: 814 source: culturax sl/iso-8859-16: language: sl encoding: iso-8859-16 samples_used: 25000 bigram_entries: 812 source: culturax sl/iso-8859-2: language: sl encoding: iso-8859-2 samples_used: 25000 bigram_entries: 812 source: culturax sl/mac-latin2: language: sl encoding: mac-latin2 samples_used: 25000 bigram_entries: 814 source: culturax sl/utf-8: language: sl encoding: utf-8 samples_used: 25000 bigram_entries: 813 source: culturax sl/windows-1250: language: sl encoding: windows-1250 samples_used: 25000 bigram_entries: 813 source: culturax sr/cp855: language: sr encoding: cp855 samples_used: 25000 bigram_entries: 872 source: culturax sr/cp866: language: sr encoding: cp866 samples_used: 25000 bigram_entries: 782 source: culturax sr/iso-8859-5: language: sr encoding: iso-8859-5 samples_used: 25000 bigram_entries: 872 source: culturax sr/mac-cyrillic: language: sr encoding: mac-cyrillic samples_used: 25000 bigram_entries: 872 source: culturax sr/utf-8: language: sr encoding: utf-8 samples_used: 25000 bigram_entries: 211 source: culturax sr/windows-1251: language: sr encoding: windows-1251 samples_used: 25000 bigram_entries: 872 source: culturax sv/cp1140: language: sv encoding: cp1140 samples_used: 25000 bigram_entries: 915 source: culturax sv/cp437: language: sv encoding: cp437 samples_used: 25000 bigram_entries: 917 source: culturax sv/cp500: language: sv encoding: cp500 samples_used: 25000 bigram_entries: 915 source: culturax sv/cp850: language: sv encoding: cp850 samples_used: 25000 bigram_entries: 915 source: culturax sv/cp858: language: sv encoding: cp858 samples_used: 25000 bigram_entries: 915 source: culturax sv/hp-roman8: language: sv encoding: hp-roman8 samples_used: 25000 bigram_entries: 917 source: culturax sv/iso-8859-1: language: sv encoding: iso-8859-1 samples_used: 25000 bigram_entries: 915 source: culturax sv/iso-8859-15: language: sv encoding: iso-8859-15 samples_used: 25000 bigram_entries: 915 source: culturax sv/mac-roman: language: sv encoding: mac-roman samples_used: 25000 bigram_entries: 915 source: culturax sv/utf-8: language: sv encoding: utf-8 samples_used: 25000 bigram_entries: 897 source: culturax sv/windows-1252: language: sv encoding: windows-1252 samples_used: 25000 bigram_entries: 915 source: culturax tg/koi8-t: language: tg encoding: koi8-t samples_used: 25000 bigram_entries: 801 source: culturax tg/utf-8: language: tg encoding: utf-8 samples_used: 25000 bigram_entries: 251 source: culturax th/cp874: language: th encoding: cp874 samples_used: 25000 bigram_entries: 2778 source: culturax th/tis-620: language: th encoding: tis-620 samples_used: 25000 bigram_entries: 2778 source: culturax th/utf-8: language: th encoding: utf-8 samples_used: 25000 bigram_entries: 114 source: culturax tr/cp1026: language: tr encoding: cp1026 samples_used: 25000 bigram_entries: 1153 source: culturax tr/cp1140: language: tr encoding: cp1140 samples_used: 25000 bigram_entries: 1041 source: culturax tr/cp857: language: tr encoding: cp857 samples_used: 25000 bigram_entries: 1153 source: culturax tr/iso-8859-3: language: tr encoding: iso-8859-3 samples_used: 25000 bigram_entries: 1153 source: culturax tr/iso-8859-9: language: tr encoding: iso-8859-9 samples_used: 25000 bigram_entries: 1153 source: culturax tr/mac-turkish: language: tr encoding: mac-turkish samples_used: 25000 bigram_entries: 1153 source: culturax tr/utf-8: language: tr encoding: utf-8 samples_used: 25000 bigram_entries: 823 source: culturax tr/windows-1254: language: tr encoding: windows-1254 samples_used: 25000 bigram_entries: 1153 source: culturax uk/cp1125: language: uk encoding: cp1125 samples_used: 25000 bigram_entries: 1367 source: culturax uk/cp855: language: uk encoding: cp855 samples_used: 25000 bigram_entries: 1394 source: culturax uk/cp866: language: uk encoding: cp866 samples_used: 25000 bigram_entries: 1045 source: culturax uk/iso-8859-5: language: uk encoding: iso-8859-5 samples_used: 25000 bigram_entries: 1367 source: culturax uk/koi8-u: language: uk encoding: koi8-u samples_used: 25000 bigram_entries: 1365 source: culturax uk/mac-cyrillic: language: uk encoding: mac-cyrillic samples_used: 25000 bigram_entries: 1394 source: culturax uk/utf-8: language: uk encoding: utf-8 samples_used: 25000 bigram_entries: 273 source: culturax uk/windows-1251: language: uk encoding: windows-1251 samples_used: 25000 bigram_entries: 1392 source: culturax ur/cp1006: language: ur encoding: cp1006 samples_used: 25000 bigram_entries: 19 source: culturax ur/utf-8: language: ur encoding: utf-8 samples_used: 25000 bigram_entries: 237 source: culturax vi/utf-8: language: vi encoding: utf-8 samples_used: 25000 bigram_entries: 674 source: culturax vi/windows-1258: language: vi encoding: windows-1258 samples_used: 25000 bigram_entries: 799 source: culturax zh/big5hkscs: language: zh encoding: big5hkscs samples_used: 25000 bigram_entries: 4957 source: culturax zh/gb18030: language: zh encoding: gb18030 samples_used: 25000 bigram_entries: 5706 source: culturax zh/hz-gb-2312: language: zh encoding: hz-gb-2312 samples_used: 25000 bigram_entries: 3194 source: culturax zh/utf-8: language: zh encoding: utf-8 samples_used: 25000 bigram_entries: 2517 source: culturax