"Empowering Moroccan Languages through Open Source AI"
Explore ProjectsAdvanced datasets, neural models, and comprehensive tools for Moroccan Darija natural language processing and understanding.
View Project →Cutting-edge resources and transformer models for Tamazight language processing, preserving and digitalizing Berber heritage.
View Project →These languages are underrepresented in NLP research and applications. We aim to build comprehensive open datasets and state-of-the-art models to empower AI applications for Moroccan languages, preserving linguistic diversity in the digital age.
Everyone! Developers, linguists, data scientists, students, and language enthusiasts are welcome to contribute via GitHub or Hugging Face. We believe in community-driven development.
All models are publicly available on Hugging Face with comprehensive documentation. You can easily integrate them into your NLP projects, chatbots, translation systems, or AI applications using our APIs.
Absolutely! All datasets, models, training code, and documentation are open-source under permissive licenses. We believe in transparency and community collaboration.