lingo.lol is one of the many independent Mastodon servers you can use to participate in the fediverse.
A place for linguists, philologists, and other lovers of languages.

Server stats:

66
active users

#tesseract

0 posts0 participants0 posts today
phildini<p>Then I was asked for <a href="https://wandering.shop/tags/berkeley" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>berkeley</span></a>, and this was the first real inflection point for the project.</p><p>Berkeley didn't use Legistar. It didn't use any system I had seen before, and it had minutes going back to 1905.</p><p>This was going to be prohibitively expensive using AWS' OCR tool, so I had to get creative.</p><p>This was where I started exploring <a href="https://wandering.shop/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a>, and building a pipeline for this project that could run entirely on one machine.</p><p>3/n</p>
UK<p><a href="https://www.europesays.com/uk/96884/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="">europesays.com/uk/96884/</span><span class="invisible"></span></a> 45 years ago, Carl Sagan beautifully explained the fourth dimension with just an apple. <a href="https://pubeurope.com/tags/4thDimension" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>4thDimension</span></a> <a href="https://pubeurope.com/tags/AlbertEinstein" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AlbertEinstein</span></a> <a href="https://pubeurope.com/tags/Apple" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Apple</span></a> <a href="https://pubeurope.com/tags/CarlSagan" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CarlSagan</span></a> <a href="https://pubeurope.com/tags/dimensions" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dimensions</span></a> <a href="https://pubeurope.com/tags/Physics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Physics</span></a> <a href="https://pubeurope.com/tags/Science" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Science</span></a> <a href="https://pubeurope.com/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a> <a href="https://pubeurope.com/tags/TheoryOfRelativity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TheoryOfRelativity</span></a> <a href="https://pubeurope.com/tags/time" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>time</span></a> <a href="https://pubeurope.com/tags/UK" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>UK</span></a> <a href="https://pubeurope.com/tags/UnitedKingdom" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>UnitedKingdom</span></a> <a href="https://pubeurope.com/tags/ViralVideos" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ViralVideos</span></a> <a href="https://pubeurope.com/tags/YouTube" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>YouTube</span></a></p>
Eugen Rochko<p>Looks like <a href="https://mastodon.social/tags/TheDearHunter" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TheDearHunter</span></a> is coming back to Europe this year at <a href="https://mastodon.social/tags/BeProgMyFriend" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BeProgMyFriend</span></a> in Spain and <a href="https://mastodon.social/tags/Euroblast" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Euroblast</span></a> in Germany, both in September. Alongside <a href="https://mastodon.social/tags/TesseracT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TesseracT</span></a>!</p>
fyre_festivals<p>New Artist announced for Motocultor Festival 2025: 🔥 Tesseract 🔥</p><p>🎶 Listen to the current LineUp on YouTube and Spotify: <a href="https://fyrefestivals.co" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">fyrefestivals.co</span><span class="invisible"></span></a><br>🎟️ Get your Tickets now: <a href="https://prf.hn/l/EJnYMdO" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">prf.hn/l/EJnYMdO</span><span class="invisible"></span></a></p><p><a href="https://mastodon.social/tags/Motocultor_Festival_2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Motocultor_Festival_2025</span></a> <a href="https://mastodon.social/tags/Tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tesseract</span></a> <a href="https://mastodon.social/tags/fyre_festivals" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>fyre_festivals</span></a> <a href="https://mastodon.social/tags/livemusic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>livemusic</span></a> <a href="https://mastodon.social/tags/youtube" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>youtube</span></a> <a href="https://mastodon.social/tags/spotify" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>spotify</span></a> <a href="https://mastodon.social/tags/music" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>music</span></a> <a href="https://mastodon.social/tags/musicfestivals" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>musicfestivals</span></a> <a href="https://mastodon.social/tags/playlist" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>playlist</span></a> <a href="https://mastodon.social/tags/tickets" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tickets</span></a> <a href="https://mastodon.social/tags/announcement" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>announcement</span></a></p>
Tommi Nieminen<p>I’m still annoyed with the state of <a href="https://mastodontti.fi/tags/OCR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR</span></a> in <a href="https://mastodontti.fi/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a> (or <a href="https://mastodontti.fi/tags/FLOSS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FLOSS</span></a> in general). Not that the need for OCR’ing hasn’t diminished by the years, as more and more of publications are already in electronic form, but every once in a while a need arises. <a href="https://mastodontti.fi/tags/Tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tesseract</span></a>’s quality is <a href="https://mastodontti.fi/tags/abysmal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>abysmal</span></a> (and not in Joey’s sense). <a href="https://mastodontti.fi/tags/ABBYYFineReader" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ABBYYFineReader</span></a> used to be the best in <a href="https://mastodontti.fi/tags/Windows" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Windows</span></a>, and once upon a time they provided a <a href="https://mastodontti.fi/tags/CLI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CLI</span></a>-usable OCR engine for Linux too, but not any more. <a href="https://mastodontti.fi/tags/atkjuttuja" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>atkjuttuja</span></a> <a href="https://mastodontti.fi/tags/computers" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computers</span></a></p>
Daniela Schneider<p>Hi <a href="https://fedihum.org/tags/histodons" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>histodons</span></a>,<br>I need your expertise. We want to integrate an <a href="https://fedihum.org/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</span></a> <a href="https://fedihum.org/tags/ocr" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ocr</span></a> tool into our <a href="https://fedihum.org/tags/useGalaxy" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>useGalaxy</span></a> Platform so you can better analyse your texts, etc.<br>I worked with <a href="https://fedihum.org/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a> some years ago, and I heard about <a href="https://fedihum.org/tags/ocr4all" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ocr4all</span></a>. <br>Do you have experience with any of these - or other recommendations?<br>We are also integrating <a href="https://fedihum.org/tags/tranksribus" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tranksribus</span></a> via API but want another ocr-specific option.<br>Looking forward to your experiences! </p><p><span class="h-card" translate="no"><a href="https://xn--baw-joa.social/@galaxyfreiburg" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>galaxyfreiburg</span></a></span> <br><span class="h-card" translate="no"><a href="https://nfdi.social/@NFDI4Memory" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>NFDI4Memory</span></a></span></p>
Eugen Rochko<p><a href="https://mastodon.social/tags/TesseracT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TesseracT</span></a>, <a href="https://mastodon.social/tags/Leprous" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Leprous</span></a>, <a href="https://mastodon.social/tags/GreenLung" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GreenLung</span></a> and <a href="https://mastodon.social/tags/Sungazer" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Sungazer</span></a> among others announced for this year's <a href="https://mastodon.social/tags/ArcTanGent" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArcTanGent</span></a>. Tempting 😬</p>
Tuomo H<p>Tesseractia katsomaan. Kaksi ekaa levyä iski lujaa, mutta livenä en ole nähnyt. Nyt keikan lähestyessä ottanut haltuun uusinta ja yhtä vähän vanhempaa lättyä (Sonder). Toimivat, etenkin uusin!</p><p><a href="https://mementomori.social/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a> <a href="https://mementomori.social/tags/TheWarOfBeing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TheWarOfBeing</span></a> <a href="https://mementomori.social/tags/djent" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>djent</span></a> <a href="https://mementomori.social/tags/musadontti" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>musadontti</span></a></p>
Trevor Burrows<p><span class="h-card" translate="no"><a href="https://fedihum.org/@lavaeolus" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>lavaeolus</span></a></span> have worked with <a href="https://techhub.social/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a> but not via a GUI - Thanks for this.</p>
Tom :damnified:<p>My Album Of The Year is: "Lingua Ignota Pt. 1" by Persefone. </p><p>I chose the album as my AOTY because I was eagerly awaiting the release and not a single song on the EP disappoints! Every single one picks me up and combines the familiar Persefone sound without being stingy with refreshing new elements. I attended their live concert shortly after the releases and couldn't be happier! Great band, awesome show, nice crowd! Can't wait for Pt. 2! 😍 </p><p>There were 3 more candidates for my AOTY. In order of preference:</p><p>TesseracT - War of Being<br>DVNE - Voidkind<br>VOLA - Friend of a Phantom</p><p><a href="https://metalhead.club/tags/aoty" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>aoty</span></a> <a href="https://metalhead.club/tags/aoty2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>aoty2025</span></a> <a href="https://metalhead.club/tags/metal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>metal</span></a> <a href="https://metalhead.club/tags/album" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>album</span></a> <a href="https://metalhead.club/tags/releases" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>releases</span></a> <a href="https://metalhead.club/tags/persefone" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>persefone</span></a> <a href="https://metalhead.club/tags/vola" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>vola</span></a> <a href="https://metalhead.club/tags/dvne" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dvne</span></a> <a href="https://metalhead.club/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a> <a href="https://metalhead.club/tags/music" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>music</span></a></p>
Küpa<p>chambear escuchando <a href="https://zirk.us/tags/Tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tesseract</span></a> está super bien. le echo bolas con ganas.</p>
Kir4ik52 :blobfoxsanta:<p>Pdf-extract-API </p><p>Проект предлагает инструмент для конвертации изображений и PDF-файлов в текст форматов Markdown и JSON с высокой точностью, включая поддержку табличных данных и математических формул. </p><p>Он основан на FastAPI, использует Celery для асинхронной обработки и Redis для кэширования результатов OCR, предоставляя различные стратегии для конвертации, такие как Marker, Surya-OCR и Tesseract, а также возможность удаления персонально идентифицируемой информации. </p><p>src: <a href="https://github.com/CatchTheTornado/pdf-extract-api" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/CatchTheTornado/pdf</span><span class="invisible">-extract-api</span></a></p><p><a href="https://mastodon.ml/tags/blacktriangle" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>blacktriangle</span></a> <a href="https://mastodon.ml/tags/opensorce" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensorce</span></a> <a href="https://mastodon.ml/tags/github" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>github</span></a> <a href="https://mastodon.ml/tags/OCR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR</span></a> <a href="https://mastodon.ml/tags/tesseract_ocr" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract_ocr</span></a> <a href="https://mastodon.ml/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a> <a href="https://mastodon.ml/tags/markdown" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>markdown</span></a> <a href="https://mastodon.ml/tags/pdf" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pdf</span></a> <a href="https://mastodon.ml/tags/fastapi" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>fastapi</span></a> <a href="https://mastodon.ml/tags/json" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>json</span></a> <a href="https://mastodon.ml/tags/marker" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>marker</span></a> <a href="https://mastodon.ml/tags/Surya" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Surya</span></a>-OCR <a href="https://mastodon.ml/tags/Celery" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Celery</span></a></p>
The Krononaut Moon Project 🌑<p><a href="https://me.dm/tags/4dToys" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>4dToys</span></a>: a <a href="https://me.dm/tags/Box" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Box</span></a> of <a href="https://me.dm/tags/Four" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Four</span></a> <a href="https://me.dm/tags/Dimensional" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Dimensional</span></a> <a href="https://me.dm/tags/Toys" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Toys</span></a></p><p>We've shared this <a href="https://me.dm/tags/video" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>video</span></a> before, but it's one of our favorites on the problem of <a href="https://me.dm/tags/visualizing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>visualizing</span></a> or <a href="https://me.dm/tags/conceptualizing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>conceptualizing</span></a> higher <a href="https://me.dm/tags/dimensional" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dimensional</span></a> <a href="https://me.dm/tags/geometries" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>geometries</span></a>. The 4th dimension is not always <a href="https://me.dm/tags/Time" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Time</span></a>, but is perpendicular to the lower 3. Watch as these objects slip in &amp; out of our <a href="https://me.dm/tags/World" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>World</span></a>, like <a href="https://me.dm/tags/TimeTravelers" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TimeTravelers</span></a>!</p><p>🔗 <a href="https://www.youtube.com/watch?v=0t4aKJuKP0Q" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=0t4aKJuKP0</span><span class="invisible">Q</span></a> 02 Jun 2017 <br>🔗 <a href="https://Wikipedia.org/wiki/Four-dimensional_space" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">Wikipedia.org/wiki/Four-dimens</span><span class="invisible">ional_space</span></a> </p><p><a href="https://me.dm/tags/Community" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Community</span></a> <a href="https://me.dm/tags/TimeTravel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TimeTravel</span></a> <a href="https://me.dm/tags/Research" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Research</span></a> <a href="https://me.dm/tags/4d" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>4d</span></a> <a href="https://me.dm/tags/vr" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>vr</span></a> <a href="https://me.dm/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a> <a href="https://me.dm/tags/hypercube" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>hypercube</span></a> <a href="https://me.dm/tags/hypersphere" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>hypersphere</span></a> <a href="https://me.dm/tags/KrononautMoon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KrononautMoon</span></a></p>
Terence Eden<p>Hey, <a href="https://mastodon.social/tags/Android" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Android</span></a> friends.</p><p>Can anyone recommend a recently updated Text Recognition / OCR app which is open source?</p><p>All the ones on F-Droid are outdated. I need something which works offline rather than posting to the cloud.</p><p>Any thoughts?</p><p><a href="https://mastodon.social/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a></p>
Eugen Rochko<p>Greetings from <a href="https://mastodon.social/tags/RadarFestival" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RadarFestival</span></a>! <a href="https://mastodon.social/tags/TesseracT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TesseracT</span></a></p>
nbAt Code4Lib 2024, Zoe Tucker and Kristian Allen from UCLA Library did a presentation on their <a class="hashtag" href="https://social.biblioco.de/tag/opensource" rel="nofollow noopener" target="_blank">#OpenSource</a> <a class="hashtag" href="https://social.biblioco.de/tag/metadata" rel="nofollow noopener" target="_blank">#metadata</a> extraction pipeline for automated indexing of digital materials with complex layouts.<br><a href="https://yewtu.be/watch?v=tujc_9nVg3o&amp;t=10445" rel="nofollow noopener" target="_blank">https://yewtu.be/watch?v=tujc_9nVg3o&amp;t=10445</a><br>In their second iteration they chose the following components in order to improve the results: PaddleOCR (instead of <a class="hashtag" href="https://social.biblioco.de/tag/tesseract" rel="nofollow noopener" target="_blank">#Tesseract</a>) for <a class="hashtag" href="https://social.biblioco.de/tag/ocr" rel="nofollow noopener" target="_blank">#OCR</a>, Amazon Science ReFinED (instead of <a class="hashtag" href="https://social.biblioco.de/tag/spacy" rel="nofollow noopener" target="_blank">#spaCy</a>) for <a class="hashtag" href="https://social.biblioco.de/tag/ner" rel="nofollow noopener" target="_blank">#NER</a>, and Ollama (instead of <a class="hashtag" href="https://social.biblioco.de/tag/chatgpt" rel="nofollow noopener" target="_blank">#ChatGPT</a> and <a class="hashtag" href="https://social.biblioco.de/tag/gemini" rel="nofollow noopener" target="_blank">#Gemini</a>) for metadata extraction in Dublin Core or MODS.<br>Their experimental toolkit is available on GitHub as docker container running a JupyterLab environment and was implemented in Python.<br><a href="https://github.com/UCLALibrary/metadata-extraction-lab" rel="nofollow noopener" target="_blank">https://github.com/UCLALibrary/metadata-extraction-lab</a><br><a class="hashtag" href="https://social.biblioco.de/tag/aiinlibraries" rel="nofollow noopener" target="_blank">#AIinLibraries</a> <a class="hashtag" href="https://social.biblioco.de/tag/libraries" rel="nofollow noopener" target="_blank">#Libraries</a> <a class="hashtag" href="https://social.biblioco.de/tag/generativeai" rel="nofollow noopener" target="_blank">#GenerativeAI</a> <a class="hashtag" href="https://social.biblioco.de/tag/llms" rel="nofollow noopener" target="_blank">#LLMs</a> <a class="hashtag" href="https://social.biblioco.de/tag/ai" rel="nofollow noopener" target="_blank">#AI</a> <a class="hashtag" href="https://social.biblioco.de/tag/cataloging" rel="nofollow noopener" target="_blank">#Cataloging</a> <a class="hashtag" href="https://social.biblioco.de/tag/cataloguing" rel="nofollow noopener" target="_blank">#Cataloguing</a> <a class="hashtag" href="https://social.biblioco.de/tag/c4l24" rel="nofollow noopener" target="_blank">#c4l24</a>
nbZoe Tucker und Kristian Allen von der UCLA Library haben auf der Code4Lib 2024 eine <a class="hashtag" href="https://social.biblioco.de/tag/opensource" rel="nofollow noopener" target="_blank">#OpenSource</a> <a class="hashtag" href="https://social.biblioco.de/tag/metadaten" rel="nofollow noopener" target="_blank">#Metadaten</a>-Extraktions-Pipeline zur automatischen <a class="hashtag" href="https://social.biblioco.de/tag/erschließung" rel="nofollow noopener" target="_blank">#Erschließung</a> von Digitalisaten mit komplexen Layouts vorgestellt.<br><a href="https://yewtu.be/watch?v=tujc_9nVg3o&amp;t=10445" rel="nofollow noopener" target="_blank">https://yewtu.be/watch?v=tujc_9nVg3o&amp;t=10445</a><br>In einer zweiten Iteration haben sie sich für die Kombination folgender Komponenten entschieden, um bessere Ergebnisse zu erzielen: PaddleOCR (statt <a class="hashtag" href="https://social.biblioco.de/tag/tesseract" rel="nofollow noopener" target="_blank">#Tesseract</a>) für <a class="hashtag" href="https://social.biblioco.de/tag/ocr" rel="nofollow noopener" target="_blank">#OCR</a>, Amazon Science ReFinED (statt <a class="hashtag" href="https://social.biblioco.de/tag/spacy" rel="nofollow noopener" target="_blank">#spaCy</a>) für <a class="hashtag" href="https://social.biblioco.de/tag/ner" rel="nofollow noopener" target="_blank">#NER</a> und Ollama (statt <a class="hashtag" href="https://social.biblioco.de/tag/chatgpt" rel="nofollow noopener" target="_blank">#ChatGPT</a> und <a class="hashtag" href="https://social.biblioco.de/tag/gemini" rel="nofollow noopener" target="_blank">#Gemini</a>) für die Metadaten-Generierung in Dublin Core oder MODS.<br>Das experimentelle Toolkit steht auf GitHub als Docker-Container mit Jupyter Lab Umgebung bereit und wurde in Python umgesetzt: <a href="https://github.com/UCLALibrary/metadata-extraction-lab" rel="nofollow noopener" target="_blank">https://github.com/UCLALibrary/metadata-extraction-lab</a><br><a class="hashtag" href="https://social.biblioco.de/tag/kiinbibliotheken" rel="nofollow noopener" target="_blank">#KIinBibliotheken</a> <a class="hashtag" href="https://social.biblioco.de/tag/bibliotheken" rel="nofollow noopener" target="_blank">#Bibliotheken</a> <a class="hashtag" href="https://social.biblioco.de/tag/generativeki" rel="nofollow noopener" target="_blank">#GenerativeKI</a> <a class="hashtag" href="https://social.biblioco.de/tag/llms" rel="nofollow noopener" target="_blank">#LLMs</a> <a class="hashtag" href="https://social.biblioco.de/tag/ki" rel="nofollow noopener" target="_blank">#KI</a> <a class="hashtag" href="https://social.biblioco.de/tag/erschliessung" rel="nofollow noopener" target="_blank">#Erschliessung</a> <a class="hashtag" href="https://social.biblioco.de/tag/katalogisierung" rel="nofollow noopener" target="_blank">#Katalogisierung</a> <a class="hashtag" href="https://social.biblioco.de/tag/c4l24" rel="nofollow noopener" target="_blank">#c4l24</a>
Philipp Zumstein<p>The <a href="https://openbiblio.social/tags/Zotero" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Zotero</span></a> <a href="https://openbiblio.social/tags/OCR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR</span></a> Plugin is now compatible with Zotero 7. 🎉 Thank you <span class="h-card" translate="no"><a href="https://openbiblio.social/@sw" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>sw</span></a></span> and A. Borel for all the work on this and releasing version 0.7.0 of the plugin. <a href="https://github.com/UB-Mannheim/zotero-ocr" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/UB-Mannheim/zotero-</span><span class="invisible">ocr</span></a> <a href="https://openbiblio.social/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a></p>
Vanessa<p><a href="https://metalhead.club/tags/TuneTuesday" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TuneTuesday</span></a> <a href="https://metalhead.club/tags/SongBaton" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SongBaton</span></a> <span class="h-card" translate="no"><a href="https://metalhead.club/@Kitty" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>Kitty</span></a></span> <br><a href="https://metalhead.club/tags/ProgressiveMetal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ProgressiveMetal</span></a> <a href="https://metalhead.club/tags/ProgMetal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ProgMetal</span></a></p><p>I always think of these together. Thankfully they combined them into one track on Portals</p><p><a href="https://metalhead.club/tags/TesseracT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TesseracT</span></a><br><a href="https://songwhip.com/tesseract/of-matter-retrospect" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">songwhip.com/tesseract/of-matt</span><span class="invisible">er-retrospect</span></a></p><p><a href="https://songwhip.com/tesseract/of-matter-resist" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">songwhip.com/tesseract/of-matt</span><span class="invisible">er-resist</span></a></p>
AngryGirlK<p>I heard we’re doing <a href="https://metalhead.club/tags/ProgTuesday" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ProgTuesday</span></a>! I love that. And I fucking love <a href="https://metalhead.club/tags/Tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tesseract</span></a> so here’s my Prog Tuesday tune. <br>I can definitely dig this trend. Thanks <span class="h-card" translate="no"><a href="https://metalhead.club/@DXMacGuffin" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>DXMacGuffin</span></a></span> 🙏🏽</p><p>Everyone should listen to Tesseract if you don’t mind cleans with some fantastic proggy melodies and super tight drums mixed in. </p><p><a href="https://metalhead.club/tags/ProgTuesday" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ProgTuesday</span></a> </p><p><a href="https://youtu.be/UnkpPIupQxM?si=RQ7YoKePmszQXlja" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">youtu.be/UnkpPIupQxM?si=RQ7YoK</span><span class="invisible">ePmszQXlja</span></a></p>