Phonon-1 released: 782M param model beats Whisper 2x its size
DevvMandal · x · 2026-08-29
Fermion AI has released the open-source speech recognition model Phonon-1.
Key Features:
- Performance: A 782 million parameter model with a 415MB download size. It claims to be more accurate than Whisper models twice its size.
- Speed: Can transcribe one hour of audio in about two minutes on a MacBook Air.
- Open Source: Weights are released under the Apache 2.0 license.
More from Models
- FastVideo Releases FastH3 V1: 4-Step Sparse Distilled Model — Recoil42 · 2026-08-29
- Rumor: Upcoming Gemini 3.5+ versions are distilled from 3.5 Pro — haider1 · 2026-08-29
- Tested: GLM-5.3 Flash with SIMURG integration drastically reduces hallucinations — Mysterious-Rub2619 · 2026-08-29
- Debugging: MTP enabled on Qwen 3.6 9B caused tool calling failures — OvertaxedOne · 2026-08-29
- GLM-5.3 Launches on Tinker with 256k Context — simonguozirui · 2026-08-29
- Grok 4.6 launches on web, iOS, and Android with agentic improvements — SpaceXAI · 2026-08-29