DSN 2026 spoken language identification

mms-300m encoder truncated to 12 layers, fine-tuned for 13-way language ID. Validation language-weighted F1 0.596.

Labels: yor ibo hau ego anw efi ibb idu igl nup tiv urh other

Training data: Data-Science-Nigeria/dsn-2026-lid-train (train split). External datasets used: none.

Downloads last month
-
Safetensors
Model size
0.2B params
Tensor type
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support