What tools to use for audio processing and training?

I soon start a new job and the task is to build an app which recognizes horse diseases. They are equipped with sensors on their heart and so to measure the sound and vibration of the heartbeat. Iḿ new to ML and AI and it would be cool to get some tips on where to start or which libraries to use for such a task. Most audio processing models and tools I have found so far are more related to speech recognition.

I did a quick internet search for “ML ECG analysis”, and found this paper.

It might be a useful starting point to learn what the challenges are for this type of task.