AI and NLP solutions
for oriental languages

Delivering new technologies for non-western languages. Dedicated to organizations, companies and cultural heritage professionals.

Discover

Text recognition of printed and handwritten texts (OCR/HTR)

Calfa developed an Artificial Intelligence for Arabic, Armenian, Georgian, Syriac etc. This technology is able to analyse the page layout and to read the text from the document, giving it a new, digital potential.

Discover

Documents and Content Analysis

We develop AI models dedicated to document analysis, content detection and text analysis (morphological analysis, Named Entity Recognition) for non-Western languages.

Discover

Research and open access materials

We provide open acces tools and models for research. We also make available for downloading multiple datasets and research materials.

Discover

Our actions for cultural heritage preservation

We lead or co-finance projects to preserve written or printed cultural heritage. Discover our digitization and conservation actions.

Discover

Our latest projects

To rescue 20th Century press archives from the Armenian diaspora

Samuelian Bookshop (Paris)

Workshop about AI and cultural heritage for TUMO students

A training course on AI basics mixed with armenian cultural heritage (Yerevan)

Digitization of AGBU Nubar Library's catalog

Creation of a digital catalog by OCR-izing and classifying paper bibliographic records

Indexing et digitizing the Dulaurier Collection of the BULAC

Bibliothèque Universitaire des Langues et Civilisations Orientales (Paris)

About Calfa

Founded in 2014, Calfa is developing text detection and automated analysis technologies for manuscripts written in oriental languages. Our team is composed of PhD-students and engineers in Artificial Intelligence, specialists of deep learning. We are today improving our expertise in text recognition and digitization for the needs of our partners, facing a lack of performing tools dedicated to oriental languages.

Learn more about Calfa