Xiaomi Open-Sources MiDashengLM-Spatial, an Audio Model That Hears Both What and Where

T2Covered by 1 source · first reported by China: SCMP Tech / TechNode / Pandaily / KrASIA / Sixth Tone at 16 Oct, 03:04 UTC

Built on MiDashengLM-7B with a new Spatial-Dasheng encoder, the Apache 2.0 model pairs general audio understanding with sound direction, distance and movement.

Sources

• T2Xiaomi Open-Sources MiDashengLM-Spatial, an Audio Model That Hears Both What and WhereChina: SCMP Tech / TechNode / Pandaily / KrASIA / Sixth Tone16 Oct, 03:04