Tsakonian Digital
← Back to dictionary

About Tsakonian Digital

Tsakonian Digital is a project that aims to support efforts to preserve and revive the Tsakonian language, the last surviving descendant of Ancient Doric, by providing digital resources and tools for learning and using the Tsakonian language. The project is led by Jaime García Chaparro, a Senior Data Scientist based in Madrid, Spain, who focuses on the technical development (data collection, model training, website development), and Professor Maxim Kisilier, based in Saint Petersburg, who covers the linguistic and institutional side as one of the world's leading experts on Tsakonian. Much of the material used in the project has been provided either by the Tsakonian Archive or by local resident Mr. Panos Marneris, whose efforts to preserve the language and support Tsakonian Digital are deeply appreciated.

Since its launch in July 2023, the project has developed the following tools and resources:

  1. The first online dictionary for the language, translating to and from Greek, as well as English and Spanish, both firsts in the history of Tsakonian. It is available for free on our website.
  2. The first neural machine translation model capable of translating between Tsakonian and Greek in both directions, making it the first AI model ever trained on Tsakonian. The model is fully open-source and available for free download on HuggingFace.
  3. A Tsakonian keyboard extension, which allows typing Tsakonian using Kostakis' orthography on computers. The extension is available for free in the corresponding section of our website.

The project was broadly divided into three stages:

  1. Linguistic stage: deals with the basic theoretical principles for studying the language, including research into its current state and available resources, acquiring core linguistic knowledge with particular attention to the different orthographies and dialects, and creating supporting material for learning the language, including a digital dictionary.
  2. Data collection stage: aims to gather raw information to be stored in databases for use in later processes. The main goal was to build a parallel corpus storing a large volume of Tsakonian sentences together with their corresponding translations into Modern Greek.
  3. AI development stage: this phase focuses on training a Large Language Model (LLM) system capable of performing translation tasks and other language-processing functions.

So far, yearly progress has been presented at the closing ceremony of the Tsakonian Summer School, held in Leonidio every early August. In 2024, the first public version of the dictionary was presented. In 2025, the AI translation model was presented, with a live demonstration of its capabilities through a short conversation in Tsakonian with an AI. In addition, the dictionary's expansion was also publicly presented, with the addition of English and Spanish translations.

As of November 2025, the project's foundational stages have been completed, with the dictionary and the NMT model already available to the public. The team is currently focused on expanding the dictionary and improving the translation model, as well as developing new tools and resources to further support the Tsakonian language community.