VOICEPEAK Japanese Female 1, .0

Description

This was an experiment with using VOICEPEAK - a japanese ai-powered tts program - as a dataset for an RVC model. Japanese Female 1's voice model is trained on 36 minutes of audio, from 3 pitches. She has a sweet, neutral sounding voice, and her range is C3-C5. She also has a japanese accent when inferring english audio. Later iterations of this dataset will include different emotion-based models, however for now the model is only trained with a normal inflection. CHANGELOG: 7/2/2023: Released the model. You can download the model here: Reposted due to the prior thread being filled up with unrelated things.