Languages

FineParser recognizes more than 200 languages. You set which ones to expect at startup.

Setting languages

Pass the -language parameter when you start the container, with a comma-separated list of the languages your documents contain. Use the language keys from the Supported languages table.

docker run -p 8080:8080 fineparser -language "English,German"

Fewer is better

Pick only the languages your documents actually contain. Each language you add widens the character set the engine considers on every page, and that has three costs:

Slower processing. More candidate characters means more work per glyph.
Higher memory use. FineParser loads a dictionary for each language you add.
Lower accuracy. Characters from unrelated alphabets compete with the right ones, which increases the chance of a wrong match.

Supported languages

Natural languages, programming languages, and special text types all use the same -language parameter and can be combined in one list.

Natural languages

Language	Language key
Abkhaz	`Abkhaz`
Adyghe	`Adyghe`
Afrikaans	`Afrikaans`
Agul	`Agul`
Albanian	`Albanian`
Altaic	`Altaic`
Arabic (Saudi Arabia)	`Arabic`
Armenian (Eastern)	`ArmenianEastern`
Armenian (Grabar)	`ArmenianGrabar`
Armenian (Western)	`ArmenianWestern`
Avar	`Awar`
Aymara	`Aymara`
Azerbaijani (Cyrillic)	`AzeriCyrillic`
Azerbaijani (Latin)	`AzeriLatin`
Bangla	`Bangla`
Bashkir	`Bashkir`
Basque	`Basque`
Belarussian	`Belarusian`
Bemba	`Bemba`
Blackfoot	`Blackfoot`
Breton	`Breton`
Bugotu	`Bugotu`
Bulgarian	`Bulgarian`
Burmese	`Burmese`
Buryat	`Buryat`
Catalan	`Catalan`
Cebuano	`Visayan`
Chamorro	`Chamorro`
Chechen	`Chechen`
Chinese Simplified	`ChineseSimplified`
Chinese Traditional	`ChineseTraditional`
Chukcha	`Chukcha`
Chuvash	`Chuvash`
Corsican	`Corsican`
Crimean Tatar	`CrimeanTatar`
Croatian	`Croatian`
Crow	`Crow`
Czech	`Czech`
Danish	`Danish`
Dargwa	`Dargwa`
Dungan	`Dungan`
Dutch (Belgium)	`DutchBelgian`
Dutch (Netherlands)	`Dutch`
English	`English`
Eskimo (Cyrillic)	`EskimoCyrillic`
Eskimo (Latin)	`EskimoLatin`
Esperanto	`Esperanto`
Estonian	`Estonian`
Even	`Even`
Evenki	`Evenki`
Faeroese	`Faeroese`
Farsi	`Farsi`
Fijian	`Fijian`
Finnish	`Finnish`
French	`French`
Frisian	`Frisian`
Friulian	`Friulian`
Gagauz	`Gagauz`
Galician	`Galician`
Ganda	`Ganda`
Georgian	`Georgian`
German	`German`
German (Luxembourg)	`GermanLuxembourg`
German (new spelling)	`GermanNewSpelling`
Greek	`Greek`
Guarani	`Guarani`
Hani	`Hani`
Hausa	`Hausa`
Hawaiian	`Hawaiian`
Hebrew	`Hebrew`
Hungarian	`Hungarian`
Icelandic	`Icelandic`
Ido	`Ido`
Indonesian	`Indonesian`
Ingush	`Ingush`
Interlingua	`Interlingua`
Irish	`Irish`
Italian	`Italian`
Japanese	`Japanese`
Japanese (Modern)	`JapaneseModern`
Jingpo	`Tinpo`
Kabardian	`Kabardian`
Kalmyk	`Kalmyk`
Karachay-Balkar	`KarachayBalkar`
Karakalpak	`Karakalpak`
Kasub	`Kasub`
Kawa	`Kawa`
Kazakh	`Kazakh`
Khakas	`Khakas`
Khanty	`Khanty`
Kikuyu	`Kikuyu`
Kirghiz	`Kirgiz`
Kongo	`Kongo`
Korean	`Korean`
Korean (Hangul)	`KoreanHangul`
Koryak	`Koryak`
Kpelle	`Kpelle`
Kumyk	`Kumyk`
Kurdish	`Kurdish`
Lak	`Lak`
Latin	`Latin`
Latvian	`Latvian`
Latvian language written in Gothic script	`LatvianGothic`
Lezgin	`Lezgin`
Lithuanian	`Lithuanian`
Luba	`Luba`
Macedonian	`Macedonian`
Malagasy	`Malagasy`
Malay	`Malay`
Malinke	`Malinke`
Maltese	`Maltese`
Mansi	`Mansi`
Maori	`Maori`
Mari	`Mari`
Maya	`Maya`
Miao	`Miao`
Minangkabau	`Minankabaw`
Mohawk	`Mohawk`
Mongol	`Mongol`
Mordvin	`Mordvin`
Nahuatl	`Nahuatl`
Nenets	`Nenets`
Nivkh	`Nivkh`
Nogay	`Nogay`
Norwegian (Bokmal)	`NorwegianBokmal`
Norwegian (Nynorsk)	`NorwegianNynorsk`
NorwegianNynorsk and NorwegianBokmal	`Norwegian`
Nyanja	`Nyanja`
Occidental	`Occidental`
Ojibway	`Ojibway`
Old English	`OldEnglish`
Old French	`OldFrench`
Old German	`OldGerman`
Old Italian	`OldItalian`
Old Slavonic	`OldSlavonic`
Old Spanish	`OldSpanish`
Ossetian	`Ossetic`
Papiamento	`Papiamento`
Polish	`Polish`
Portuguese (Brazil)	`PortugueseBrazilian`
Portuguese (Portugal)	`PortugueseStandard`
Provencal	`Provencal`
Quechua	`Quechua`
Rhaeto-Romanic	`RhaetoRomanic`
Romanian	`Romanian`
Romanian (Moldavia)	`RomanianMoldavia`
Romany	`Romany`
Ruanda	`Ruanda`
Rundi	`Rundi`
Russian	`Russian`
Russian (old spelling)	`RussianOldSpelling`
Russian (with accents marking stress position)	`RussianWithAccent`
Sami (Lappish)	`Lappish`
Samoan	`Samoan`
Scottish Gaelic	`GaelicScottish`
Selkup	`Selkup`
Serbian (Cyrillic)	`SerbianCyrillic`
Serbian (Latin)	`SerbianLatin`
Shona	`Shona`
Sioux (Dakota)	`Sioux`
Slovak	`Slovak`
Slovenian	`Slovenian`
Somali	`Somali`
Sorbian	`Sorbian`
Sotho	`Sotho`
Spanish	`Spanish`
Sunda	`Sunda`
Swahili	`Swahili`
Swazi	`Swazi`
Swedish	`Swedish`
Tabassaran	`Tabassaran`
Tagalog	`Tagalog`
Tahitian	`Tahitian`
Tajik	`Tajik`
Tatar	`Tatar`
Thai	`Thai`
Tok Pisin	`PidginEnglish`
Tongan	`Tongan`
Tswana	`Tswana`
Tun	`Tun`
Turkish	`Turkish`
Turkmen	`Turkmen`
Turkmen (Latin)	`TurkmenLatin`
Tuvan	`Tuvin`
Udmurt	`Udmurt`
Uighur (Cyrillic)	`UighurCyrillic`
Uighur (Latin)	`UighurLatin`
Ukrainian	`Ukrainian`
Uzbek (Cyrillic)	`UzbekCyrillic`
Uzbek (Latin)	`UzbekLatin`
Vietnamese	`Vietnamese`
Welsh	`Welsh`
Wolof	`Wolof`
Xhosa	`Xhosa`
Yakut	`Yakut`
Yiddish	`Yiddish`
Zapotec	`Zapotec`
Zulu	`Zulu`

Programming languages

For source code listings, printouts, and documentation that contains code.

Language	Language key
BASIC	`Basic`
C/C++	`C++`
COBOL	`COBOL`
Fortran	`Fortran`
Java	`Java`
Pascal	`Pascal`

Special text types

For content that is not natural language, such as bank check codelines, machine-readable fonts, and formulas.

Text type	Language key
MICR CMC-7	`CMC7`
MICR E-13B	`E13B`
OCR-A	`OcrA`
OCR-B	`OcrB`
Mathematical notation	`Mathematical`
Digits only	`Digits`
Simple chemical formulas	`Chemistry`

Getting Started

Basics

Concepts

Reference

Setting languages

Fewer is better

Supported languages

Natural languages

Programming languages

Special text types

​Setting languages

​Fewer is better

​Supported languages

​Natural languages

​Programming languages

​Special text types

Setting languages

Fewer is better

Supported languages

Natural languages

Programming languages

Special text types