Run fully local audio-to-text transcription with LFM2.5-Audio-1.5B and llama.cpp on your laptop
helloiamleonie · x · 2026-09-07
Liquid4All updated its open-source cookbook demo to run LFM2.5-Audio-1.5B with llama.cpp, enabling a 100% local audio-to-text transcription CLI that needs no internet or cloud services.
The example shows how llama.cpp efficiency plus a small 1.5B audio model enables real-time transcription on edge devices like smartphones, cars, and smart home gadgets. The repo includes a quick start and example scripts, and has 2.4k GitHub stars.
More from Infra
- Musk: robot RAM demand will dwarf everything else, and 100% of superintelligence compute goes to deep space — elonmusk · 2026-10-27
- RTX 5090 hits $7K as PC gaming community goes into 'denial' over AI boom — PAstynome · 2026-10-27
- Wan2GP lands on Pinokio: 1-click AI video on 6GB GPUs — cocktailpeanut · 2026-10-27
- Wan2GP AMD one-click installer lands on Pinokio, runs AI video on 6GB VRAM — cocktailpeanut · 2026-10-27
- AWS on agent prompt caching: explicit + implicit patterns to slash token costs — AWS ML Blog · 2026-10-27
- Thieves spoofing GPS steal $100M+ in data center cargo since June — Ars Technica AI · 2026-10-27