Getting second tones, fourth tones, and umlauts to be read correctly shouldn’t be a big problem, given how the same marks are standard in the orthographies of many European languages. But first tones and third tones are a different matter. The best that can probably be hoped for at present is a more-or-less regular rendering of vowels with first- and third-tone marks as something else that can be fixed quickly through a search-and-replace procedure. <\/p>\n
Here’s an image, slightly reduced, of what was being scanned:
\n![\"scan](\"https:\/\/pinyin.info\/news\/news_photos\/2006\/05\/pinyin_ocr.gif\")
<\/p>\n
Here’s the text: Here are the results of OCR, with various language settings applied: <\/p>\n DUTCH CATALAN DANISH FINNISH FRENCH GERMAN GERMAN (SWISS) ITALIAN NYNORSK PORTUGUESE (BRAZILIAN) PORTUGUESE SPANISH There’s no clear winner. The best results, such as they are, appear to be using Dutch and Portuguese (Brazilian or standard). <\/p>\n","protected":false},"excerpt":{"rendered":" [This entry is largely for my own reference. But feel free to read on, especially if you’re interested in OCR or if you somehow happen to have a lot of Pinyin texts lying around.] What’s the best way to run … Continue reading
\nW? b\u00f9 sh\u00ec xu\u00e9zh?, b\u00f9 n\u00e9ng y?nj?ng j\u00f9di?n. D\u00e0nsh\u00ec w? y?u c\u00f3ng z\u00ecj? sh?nghu\u00f3 l? d\u00e9l\u00e1i de w? ge zh?nsh\u00ed l\u00eczi, d?u bi?om\u00edng H\u00e0nz\u00ec b\u00ecng b\u00f9 t\u00e8bi\u00e9 bi?oy\u00ec.<\/span><\/p>\n
\nW\u00d6 bu shi xu\u00e9zh\u00eb, b\u00f9 n\u00e9ng yinjing j\u00f9di\u00e4n. Danshi w\u00f6 y\u00f6u c\u00f3ng zip sh\u00ebnghu\u00f3
\nli d\u00e9l\u00e1i de w\u00fc ge zh\u00ebnsh\u00ed Iizi, d\u00f6u bi\u00e4om\u00edng Hanz\u00ec bing bu tebi\u00e9 bi\u00e4oy\u00ec.<\/p>\n
\nW6 bu shi xuezh8, bir neng yinjing jhdisn. Danshi w6 y5u cong ziji shenghu\u00f3
\nli delai de w\u00fc ge zhensh\u00ed lizi, d6u bibm\u00edng Hanzi bing bu tebie bigoyi.<\/p>\n
\nW6 bu shi xuezhe, bU neng yinjing jhdian. Danshi w6 y5u cong ziji shGnghu6
\nli delai de wii ge zhenshi Iizi, d\u00f3u bigoming Hanzi bing bu tebie biaoyi.<\/p>\n
\nW\u00d6 bu shi xuezhe, bU neng yinjing jiidi\u00e4n. Danshi w\u00f6 y\u00f6u cong ziji shGnghu6
\nIi delai de wii ge zhenshi Iizi, d\u00f6u bi\u00e4oming Hanzi bing bu tebie bi\u00e4oyi.<\/p>\n
\nW6 b\u00f9 shi xu\u00e9zh\u00eb, b\u00f9 n\u00e9ng yinjing j\u00f9dian. D\u00e0nshi wO y5u cong ziji sh\u00ebnghu6
\nli d\u00e9lai de w\u00fc ge zh\u00ebnshi Iizi, dou bigoming H\u00e0nzi bing bu t\u00e8bi\u00e9 biaoyi.<\/p>\n
\nW\u00d6 bu shi xuezhe, bU neng yinjing jiidi\u00e4n. Danshi w\u00f6 y\u00f6u cong ziji shGnghu6
\nli delai de w\u00fc ge zhenshi Iizi, d\u00f6u bi\u00e4oming Hanzi bing bu tebie bi\u00e4oyi.<\/p>\n
\nW\u00d6 bu shi xuezhe, bU neng yinjing jiidi\u00e4n. Danshi w\u00f6 y\u00f6u cong ziji shGnghu6
\nli delai de w\u00fc ge zhenshi Iizi, d\u00f6u bi\u00e4oming Hanzi bing bu tebie bi\u00e4oyi.<\/p>\n
\nW6 bu sh\u00ec xu\u00e9zhe, b\u00f9 n\u00e9ng yinjing j\u00f9dian. D\u00e0nsh\u00ec w6 y5u cong ziji sh\u00e8nghu6
\nli d\u00e9lai de wii ge zhenshi Iizi, dou bigoming H\u00e0nz\u00ec bing bu t\u00e8bi\u00e9 biaoy\u00ec.<\/p>\n
\nW6 bu shi xuezhe, bU neng yinjing jhdian. Danshi wO y5u cong ziji shGnghu6
\nli delai de wii ge zhenshi Iizi, dou biaoming Hanzi bing bu tebie biaoyi.<\/p>\n
\nW\u00d5 bu shi xu\u00e9zhe, bU n\u00e9ng yinjing j\u00f9di\u00e3n. Danshi w\u00f5 y\u00f5u c\u00f3ng ziji sh\u00e8nghu\u00f3
\nli d\u00e9l\u00e1i de w\u00fc ge zhensh\u00ed Iizi, d\u00f5u bi\u00e3om\u00edng Hanzi bing bu t\u00e8bi\u00e9 bi\u00e3oyi.<\/p>\n
\nW\u00d5 bu shi xu\u00e9zhe, bU n\u00e9ng yinjing j\u00f9di\u00e3n. Danshi w\u00f5 y\u00f5u c\u00f3ng ziji sh\u00e8nghu\u00f3
\nli d\u00e9l\u00e1i de w\u00fc ge zhensh\u00ed Iizi, d\u00f5u bi\u00e3om\u00edng Hanzi bing bu t\u00e8bi\u00e9 bi\u00e3oyi.<\/p>\n
\nW6 bu shi xu\u00e9zhe, bU n\u00e9ng yinjing jhdian. Danshi wO y5u c\u00f3ng ziji shenghu\u00f3
\nli d\u00e9l\u00e1i de w\u00fc ge zhensh\u00ed Iizi, d\u00f3u bigom\u00edng Hanzi bing bu tebi\u00e9 biaoyi.\n<\/p><\/blockquote>\n