Project Kasena
Digitizing our heritage
Project Kasena is building the first trusted digital Kasem dictionary, phrase corpus, and AI-ready language dataset — created by the community and validated by elders and teachers. A community-owned effort to preserve and future-proof the Kasem language for education, culture, and the next generation of AI tools.
20,000+
target validated entries
3 phases
dictionary to voice AI
Community
owned & validated
Digital dictionary
A mobile-first English ↔ Kasem dictionary and phrase tool for students, teachers, families, researchers, and the diaspora.
Community validation
Youth contributors submit words and phrases while elders and teachers validate accuracy, usage, and cultural meaning.
AI-ready corpus
Clean sentence pairs, dialect tags, domain terms, and cultural expressions become the foundation for future Kasem AI systems.
Roadmap
Phase 1: Dictionary and corpus
Build the MVP platform, collect words and sentence pairs, tag dialects, validate submissions, and publish a trusted Kasem language foundation.
Phase 2: Education and text AI
Use the verified corpus to support learning tools, domain-specific vocabulary, grammar support, and early translation experiments.
Phase 3: Voice and oral heritage
Collect consented audio, transcribe radio and community recordings, and prepare the foundation for future speech recognition and text-to-speech.
More projects in the pipeline
New initiatives are in progress. Stay tuned.