This application performs a speech-to-text transcription using OpenAI's Whisper-tiny and Whisper-base model on the Hailo-8/8L/10H AI accelerators, on a Raspberry Pi 5

Hailo AI forum page from March 2025 announcing Speech to Text through Whisper by using the Hailo AI accelerator included also in the AI HAT+2

This page provides instructions for running AI models powered by Hailo NPUs on Raspberry Pi 5. The Hailo NPU is an AI accelerator chip designed to run neural networks; instead of Raspberry Pi’s CPU doing the AI work, the NPU handles it more efficiently.

AI HATs are add-on boards for Raspberry Pi 5 that come with a built-in AI accelerator chip: the Hailo neural processing unit (NPU). The Hailo NPU allows Raspberry Pi 5 to run hardware-accelerated AI models locally, removing the need to send data to a remote cloud server for processing. This edge AI approach improves performance, reduces latency, and helps to keep data private.

Using **fbi** to show a custom splash screen during boot. Take a look at the comments for further configuration to tune it up more.

Because I had been previously using my Pi as a headless server, I hadn’t installed a desktop environment. I wanted to add a lightweight heads-up display to the server, and I wanted a graphical application that could operate without X, the usual graphical system on Linux.
Writing such a lightweight application required understanding how to interact more directly with my new screen, the learnings from which I’ll share here. This article is a summary of multiple sources I pieced together.

Raspberry Pi controlling small LED array. Here is using a LED strip, but the chip may be the same to move the wished module:
https://amzn.eu/d/iVcOwJG

More into the side of how to ensure that the Raspberry Pi 5 behaves correctly having an Ollama service running. Memory, CPU, Temperature... very interesting to have control over the hardware behaviour, to peek on what's important to control.

This GPIO Pinout is an interactive reference to the Raspberry Pi GPIO pins, and a guide to the Raspberry Pi's GPIO interfaces. Pinout also includes hundreds of pinouts for Raspberry Pi add-on boards, HATs and pHATs.

This tangential issue in StackOverflow shows actually how to define an own ONNX Session outside Piper TTS, and then pass it to the PiperVoice instance. This could solve the issue with multiprocessing (can't pickle the ONNX session)
Also, explains that ONNX already manages its own threads already. Maybe it's not worth to make it work in a separate Process.