There is a newer version of this record available.

Software Open Access

HeLI-OTS 1.2 with Python examples

Jauhiainen, Tommi; Jauhiainen, Heidi

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="" xmlns:oai_dc="" xmlns:xsi="" xsi:schemaLocation="">
  <dc:creator>Jauhiainen, Tommi</dc:creator>
  <dc:creator>Jauhiainen, Heidi</dc:creator>
  <dc:description>HeLI off-the-shelf language identifier with language models for 200 languages.

java -jar HeLI.jar -r &lt;infile&gt; -w &lt;outfile&gt;

The program will read the &lt;infile&gt; and classify the language of each line as one of the 200 languages it knows
and writes the results, one ISO 639-3 code per line, into file &lt;outfile&gt;.

You can use the -c option to make the program print a confidence score for the identification after each language code.

java -jar HeLI.jar -c -r &lt;infile&gt; -w &lt;outfile&gt;

You can give the list of comma-separated ISO 639-3 identifiers for relevant languages after -l option.

java -jar HeLI.jar -r &lt;infile&gt; -w &lt;outfile&gt; -l fin,swe,eng

You can give the number of top-scored languages to print after the -t option. (overrides confidence)

java -jar HeLI.jar -r &lt;infile&gt; -w &lt;outfile&gt; -l fin,swe,eng -t 2

If you omit both of the filenames, the program will read the standard input one line at a time and write the result to standard output.

It can identify c. 3000 sentences per second using one core on a 2021 laptop and around 3 gigabytes of memory.

If you use this program in producing scientific publications, please refer to: 
     title = "Evaluation of language identification methods using 285 languages",
     author = "Jauhiainen, Tommi  and
       Lind{\'e}n, Krister  and
       Jauhiainen, Heidi",
     booktitle = "Proceedings of the 21st Nordic Conference on Computational Linguistics",
     month = may,
     year = "2017",
     address = "Gothenburg, Sweden",
     publisher = "Association for Computational Linguistics",
     url = "",
     pages = "183--191",

Producing and publishing this software has been partly supported by The Finnish Research Impact Foundation Tandem Industry Academia -funding in cooperation with Lingsoft.</dc:description>
  <dc:subject>language identification</dc:subject>
  <dc:title>HeLI-OTS 1.2 with Python examples</dc:title>
All versions This version
Views 972122
Downloads 23658
Data volume 3.0 GB573.2 MB
Unique views 72498
Unique downloads 11424


Cite as