2025-03-10 12:59 AM
I need help with a project. I need to deploy a sound detection AI model to my B-U585I-IOT02A board. I want to test the model using live audio playback, im using Mimii valve dataset to train the AI. Im planning to play back the audio and test inference and see if the AI detects anomalous or normal sounds. I have trained the AI and compressed it to tflite file. But i have no idea how to use STM32. It is so confusing Im using AI chatbot to help me but i cant do it. I think i need to configure USART, MDF (for microphone) and x-cube-ai. but i dont know how to do it. Need help please.
2025-03-10 2:10 AM
Hello @jzzunn ,
I highly recommend using ST Model ZOO:
STMicroelectronics/stm32ai-modelzoo-services: AI Model Zoo services for STM32 devices
In you case you want to use the Audio event detection use case and the deployment operation mode:
Just to give you some context:
ST Model Zoo is a repository to help you train, quantize, benchmark and deploy AI to STM32 Microcontrollers.
The way it work is that you bring your own model (or one from our repository) and your data and you use the user_config.yaml file to define what you want to do:
Then you run the python script stm32ai_main.py to do what you've defined.
ST Model Zoo is splitted in 2 github repository: ST Model Zoo and ST Model Zoo services.
One contains models that you can use, the other the python scripts.
The deployment operation mode allows you to flash a complete demo firmware with your model.
You can find the firmware source files as a STM32CubeIDE project in the folder /application_code
To install ST Model Zoo services, make sure to follow the before you start:
Have a good day,
Julian