Zomi Tedim AI

Open-source natural language processing (NLP) resources for the Tedim (Zomi) language — a low-resource Chin/Kuki language spoken by the Zomi people.

Mission

Tedim currently has almost no digital-language infrastructure. This project builds open datasets and, eventually, models so that Tedim speakers can benefit from modern language technology — translation, speech tools, and text generation — in their own language.

What we're building

• Parallel text datasets — starting with Tedim–Burmese Bible verses (7,289 verse pairs from 20 books), with more sources planned
• Future work: everyday/conversational Tedim text, voice data, and baseline translation/language models

Repositories

• zomi-tedim-bible-corpus — Tedim–Burmese–English parallel Bible verse dataset

Collaboration

This project coordinates with the zolai-ai initiative to avoid duplicated effort and combine Tedim-language resources.

Contributions, corrections, and additional Tedim-language text sources are welcome — please open a discussion on any repository in this organization.

Creator

Thang Deih Piang — Zomi GPT AI creator

Contact

Maintained by Thang Deih Piang.