Home · tesseract-ocr/tesseract Wiki · GitHub
<p>Packages for over 130 languages and over 35 scripts are also available directly from the Linux distributions. The language packages are called <strong>'tesseract-ocr-langcode'</strong> and <strong>'tesseract-ocr-script-scriptcode'</strong>, where langcode is three letter language code and scriptcode is four letter script code.</p>
<p><strong>Examples:</strong> tesseract-ocr-eng (<strong>English</strong>), tesseract-ocr-ara (<strong>Arabic</strong>), tesseract-ocr-chi-sim (<strong>Simplified Chinese</strong>), tesseract-ocr-script-latn (<strong>Latin Script</strong>), tesseract-ocr-script-deva (<strong>Devanagari script</strong>), etc.</p>
<h2>Works!</h2>
<p>installed tesseract 4 with brew install tesseract</p>
<p>installed language support with brew install tesseract-lang</p>
<p>then run for example</p>
<pre style="padding-left: 30px;">tesseract -l ell page101-1024px-ETC.jpg output.txt</pre>
<p>and output.txt seems to have worked moderately well.</p>
<p> </p>