Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech

Block’s AI lab released Dessa, a full-duplex speech-to-speech model trained only on human conversation audio. It runs locally on a MacBook Pro M4 Max, but Block has published no size, benchmarks or weights. The post Block Unveils Dessa, a Full-Duplex Speech Model Trained Only on Speech appeared fir

MarkTechPostDonnerstag 08:50 · 29.10.1 Min. Lesezeit