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.

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.

Ollama Model for Catalan

The tool/function calling equivalent for Ollama, looking quite similar to Gemini

The offline Model library for Python

Similar to the previous link, but apparently there is a new way to do so in the newer 2.x versions that simplifies all internally.

Example of functions in Python to make Google Gemini to give weather forecast for a location during a chat