Description

Model was trained from 18 minutes of _clean_ 768Kbps WAV files, meaning the datasets are not from an episode or a song with post-processing. This ensures that the model could replicate as close to the actual raw recording as possible. "A model trained from good datasets beats a model trained from subpar datasets, no matter how much you trained it" note: due to her voice being mostly whispers with low pitch range, this model may not perform that well on tracks with high pitch range all were made on mangio-crepe with 120 hop