You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Per Testfile.py I've been able to convert a midi file into multiple numpy arrays of shape (64, 84, 1) which I can then run a trained model on. This will return a midi file (cycle, transfer) for each individual numpy array, which will of course only be a few seconds in length each. Is there code for combining midi files? I assume this must have been done for the examples given where full songs are converted.
The text was updated successfully, but these errors were encountered:
Hey, it is easy. You can just concatenate the numpy arrays together and then call the function save_midis. Basically, the individual numpy array is a phrase which is composed of 4 bars. Take a look at save_midis in utils.py and functions in write_midi.py.
Per Testfile.py I've been able to convert a midi file into multiple numpy arrays of shape (64, 84, 1) which I can then run a trained model on. This will return a midi file (cycle, transfer) for each individual numpy array, which will of course only be a few seconds in length each. Is there code for combining midi files? I assume this must have been done for the examples given where full songs are converted.
The text was updated successfully, but these errors were encountered: