This tool is a deep learning library for audio and music analysis, feature extraction. It supports dozens of time-frequency analysis transformation methods and hundreds of corresponding time-domain and frequency-domain feature combinations. It can be provided to deep learning networks for training, and is used to study various tasks in the audio field such as Classification, Separation, Music Information Retrieval(MIR) and ASR etc.

Cool, I want to make a guitar tuner on the mobile end. I don't know if it supports it?

Great idea, no problem at all, supporting real-time audio computing on the mobile end

How to do that? Do I need to create and train a model for this? Or some other way?

There are two methods. There are different algorithms for pitch detection in the MIR module, but you need to research and adjust this based on your own business situation; Another method can use spectral features to classify guitar pitch data. Generally speaking, CNN may have a better effect, but you can also try other networks such as LSTM.