You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Full-duplex spoken dialogue research: fine-tuning a speech model (LFM3-Audio-2B, QLoRA) toward an offline voice assistant that listens while it talks, on a 4 GB laptop GPU. Paused; code, frozen test definitions, results and a review paper.
Sổ Giỗ — the family memorial book whose ears admit what they didn't hear. Two local speech models, a deterministic Vietnamese lunar engine, and a guard that refuses to invent.