adaraai/adara-language

African language intelligence interfaces # adara-language African language intelligence: detection, translation, normalization, tokenization, dialects, code-switching. ## Status **Experimental** Classification: `INTELLIGENCE` · Visibility: `public` · License: `Apache-2.0` ## Overview Capability catalog for Twi, Ghanaian and Nigerian languages, Hausa, Yoruba, Nigerian Pidgin, Swahili, Amharic. All listed languages start as **planned** unless a README in that folder says otherwise. ## Why this exists Language processing should version independently of the HTTP platform. ## Architecture Each subpackage is an interface + tests. Resources in language-resources/ are metadata, not full corpora. ``` AFRICAN DATA ↓ LANGUAGE / SPEECH / CONTEXT ↓ MODELS ↓ EVALUATION + SAFETY ↓ API → SDK → PRODUCTS ``` See repository map in `adara-platform`. ## Installation Python 3.12. `pytest -q` ## Usage `detection/detect.py` returns planned statuses. Do not treat that as a production LID model. ## Development Use Conventional Commits and pull requests against `main`. See CONTRIBUTING.md. ## Testing Run the repository's documented test command. Do not run expensive training on every PR. ## Roadmap Documented in this README's status and in `adara-platform/ADARA-ARCHITECTURE.md`. Do not treat planned work as shipped. ## Contributing See CONTRIBUTING.md and the organization profile. ## Security See SECURITY.md. Never commit secrets, model weights, or private datasets. ## License Apache-2.0