One GPU transcribes 8.7 hours of mock GP calls in 18 minutes, 27.8x realtime

MaziyarPanahi · x · 2026-11-19

Developer MaziyarPanahi shared a fully open-source speech-to-notes pipeline benchmark: 57 mock GP calls totaling 8h 38min of audio were transcribed and drafted into notes in 18min 38s on a single GPU.

Motivation: many doctors still write clinical notes late into the night.

Related event: Open-source models transcribe 8.7 hours of clinic audio in 18 minutes on one GPU(2 posts)→

Original post →

More from coding & agent

coding & agent channel →