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.
- 27.8x faster than realtime
- Each draft was ready about 20 seconds after its call ended
- Open models only, using the same scribe stack as his previous run
Motivation: many doctors still write clinical notes late into the night.
More from coding & agent
- Hermes adapter solves a SWE-Bench Pro task in 35 tool calls where the base Qwen3.8 model failed — yb2698 · 2026-11-19
- NousResearch's Hermes adapter lifts Qwen3.8-27B agent scores: SWE-Bench Pro 29.4%→43.1% at 4× fewer tokens — yb2698 · 2026-11-19
- One Amazon EBS gp3 command scales a 10M-vector Weaviate index 26×, from 9.8 to 260 QPS — philipvollet · 2026-11-19
- Human Principal launches private beta: cryptographic proof a human is behind your AI agent — yenkel · 2026-11-19
- GPT-6.2 builds code-only 3D fairy town and a deep-sea civilization in 10–20 minutes — OpenAIDevs · 2026-11-19
- Designers are being asked to do interior design while ignoring the architecture — round · 2026-11-19