Fihris: The Arabic Manuscript Archive
Khayrallah Center

As historians continue to experiment with ways of deepening public historical understanding, they often encounter the issue of accessibility, particularly in relation to the archive. To counter the challenges posed by physical restrictions and language barriers while still preserving the heritage and memories of the Lebanese diaspora community, the Khayrallah Center set a goal: to make the Nassour Archive of Lebanese Diaspora accessible to everyone, regardless of location or language. That is why we created Fihris.org—a free, reliable resource for searching and translating Arabic manuscripts held within our collections.
Fihris revolutionizes the archive as the world knows it. Arabic-language sources are made immediately and universally available to anyone, anywhere. Users can search through thousands of manuscript images, all of which have been transcribed into digital Arabic text, and translate them into English, French, Spanish, or Portuguese. “This is the first ever full-text searchable Arabic manuscript archive, made possible through the proprietary AI model that we have developed at the Khayrallah Center,” explains Khayrallah Center director Dr. Akram Khater. “Now, you can enter one or more words, and Fihris will retrieve the dozens, hundreds, or thousands of documents that contain that/those word(s).” From there, you can view the original document, read the transcribed Arabic text, and request its translation, all on the same site.
This deceptively simple program is the result of over two years of hard work from the Khayrallah Center programming team, led by Dr. Mehreen Saeed. The process began with developing ScribeArabic, an AI program that annotates and transcribes images of Arabic manuscripts. Derived from a German handwriting recognition model called “Start, Follow, Read,” ScribeArabic took in over 500 manually annotated and transcribed images, and then began an extensive training process that involved manual cleanup of the AI predictions. After twelve months, the model achieved 85 to 95 percent accuracy, and the team expanded the dataset to hold over 4000 images. More information on the development process can be found on Dr. Saeed’s GitHub.
New manuscripts are regularly uploaded to the site, and their transcriptions are checked and confirmed by expert Arabic editors to ensure their accuracy. Along with continually adding new sources, the project’s next step will integrate our newspaper database, ArabicSearch, with Fihris to apply the same transcription and translation capabilities to the repository’s 450,000+ newspaper pages.
In future updates, Fihris will gain semantic search capabilities, allowing for conceptual searching alongside the system’s current word-for-word search capabilities. Users will also be able to type in a question and receive a historically contextualized answer from our AI “chatbot” as well as a list of relevant primary sources to answer their query. Following this, our goal is for users to be able to submit images of their own Arabic manuscripts, where Fihris will transcribe them into digital text and provide translation if needed.
Fihris represents one of many efforts supporting the Khayrallah Center’s mission: to preserve and share the extensive knowledge of the Lebanese diaspora. “One of the main reasons we launched this project is to give Arab Americans wider access to the sources of their own history,” says Dr. Khater. “Across the Americas, many Arab Americans have handwritten Arabic letters, diaries, notebooks, and other material left to them by their ancestral families. Yet they cannot access these rich memories of their families and communities because most do not know how to read Arabic, and certainly not handwritten text. So, by developing Fihris, we are able to give them complete access to these hidden-in-plain-sight stories. Now they can read it, write about it, and pass it on to the next generation.”
| The Khayrallah Center preserves and shares the stories of Lebanese immigrants in the U.S. and abroad through research projects, exhibits, documentaries, and more. |
OpenEdition suggests that you cite this post as follows:
Bridging Editor (May 6, 2026). Fihris: The Arabic Manuscript Archive. IFPH-FIHP. Retrieved May 18, 2026 from https://doi.org/10.58079/166j7

