This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.
I created a small wrapper that allows to run inference on long audio clips by analyzing a window in strides. This also includes a small class to be reused in other python code.
I created a small wrapper that allows to run inference on long audio clips by analyzing a window in strides. This also includes a small class to be reused in other python code.