Phonon-2 on-device ASR model with QAT low-bit quantization lands on HF trending
FermionResearch · hf · 2026-10-01
FermionResearch's Phonon-2 speech-to-text model is trending on Hugging Face. Built for Apple Silicon on-device deployment on the parakeet-tdt architecture, it uses quantization-aware training to ship low-bit variants, targeting local, low-resource transcription on Macs.
Related event: Open-Source Phonon-2 ASR Model Beats Whisper Large at Just 164MB(3 posts)→
More from Infra
- Padding trick lets vLLM run tp=6: 27B model at 50 tok/s on six 7900 XTX GPUs — Biomass23 · 2026-10-01
- Chutes team on Bittensor Subnet 64 may have stumbled on a new way to train models while fixing inference economics — markjeffrey · 2026-10-01
- Ornith-1.5 DFlash draft models deliver up to 2.54x lossless inference speedup — alan_ritter · 2026-10-01
- Manager locked Teams transcripts, employee used Copilot to dig JSON URL out of page source — TheBigCrowbroski · 2026-10-01
- Compute per MW comparison: Nvidia still best price/perf despite prices — Storge2 · 2026-10-01
- No signal on the Bay Bridge: AI's broad impact hinges on patchy internet access — soumitrashukla9 · 2026-10-01