idemásolok egy help részletet: WIDI performs music transcription in several steps.

First it produces some kind of spectra-like data, this is called further the "WAVE->Pitch" conversion. Now there are three different algorithms implementing this step, each of them has its own advantages and disadvantages.

Then it multiplies that spectral data by coefficients of "Equalizer", making some pitches louder and some pitches more quiet.

The third step is an actual retrieval of notes from the spectra, it is called "Pitch->MIDI" process and there are also two algorithms making that.

The final step is producing the MIDI file structure, and you can choose some attributes of the output MIDI file.