How to prepare files for a neural network?

Question

Neural networks

I found an interesting source on github for automatic correction of vocals, but did not figure out how to prepare files for auto-correction. Here is what the author writes:

Data pre-processing

The program requires frame- and note-wise pYIN pitch analyses. Please check directory ./Intonation/realworld_data/pyin for examples of these. The outputs of the Sonic Visualizer are converted from seconds to frame indices.

That is, you need a csv file with note pitch data and you need a numpy wav file to run

https://github.com/sannawag/autotuner