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

Example of Python code to process chunks of sounds on a application loop

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.