Tether Releases Offline Translation Models Supporting 19 African Languages

Tether AI Research has released a new set of open-source translation models that can run directly on consumer devices. The TranslatePsy-AfriSLM model supports 19 African languages, while the smaller TranslatePsy-EuroNano supports nine European languages.

The models are designed for on-device inference, allowing translation without continuous cloud connectivity. This approach is relevant to the broader push toward user-controlled infrastructure and reducing reliance on centralized services in the crypto industry.

Tether's African-language release targets low-resource languages and includes Hausa, Amharic, Yoruba, Lingala, Swahili, Igbo, Zulu, Somali, Oromo, Malagasy, Kinyarwanda, Xhosa, Afrikaans, Wolof, Luganda, Nyanja, Shona, Tswana, and Southern Sotho.

Tether said its 800-million-parameter African model outperformed several larger systems in internal benchmark tests. The company also removed up to 96% of low-quality open-source training data using a quality-estimation filter during the training process.