Code and instructions available here: https://github.com/albertoZurini/echo-dot-2-playground Hello there! After a few days of experimenting I was able to get a completely local voice pipeline running on an Amazon Echo Dot 2. The interesting part for this community is that the device can run `llama.cpp` alongside offline speech recognition even with its very limited hardware. The Echo Dot 2 has an ARMv7 processor and 512 MB of RAM. I compiled `llama.cpp` for `armeabi-v7a` and run the model ...