First Open-Source Diffusion ASR Model Runs 15x Faster Than Whisper
bodonoghue85 · x · 2026-07-03
interfazeai has open-sourced the first automatic speech recognition (ASR) system based on a diffusion model. By integrating DiffusionGemma and Whisper technologies, it achieves inference speeds 15 times faster than Whisper. This marks the first application of diffusion models in open-source ASR, delivering a significant speed breakthrough while maintaining Whisper's recognition quality, and paving a new technical path for real-time voice applications.
More from Models
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26
- Dev testing one skill across Opus 5.5 and Sol 6.1 finds instruction following 'all over the map' — lucasmeijer · 2026-10-26
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26
- AI search APIs ranked: top 12 within 7 points, yet prices differ nearly 7x — FinanceYF5 · 2026-10-26