Description

Usual Info: ================================= Dataset is around 8 mins of in-game dialogue. I also included that singing scene from Mass Effect 3. Speech was tested using Elevenlabs with the Matilda model. (I tried looking for a Russian accent, but didn't see one.) You may need to transpose up when inferencing, only do so if it sounds too deep. RVC Setting: ================================= * Search Feature Ratio: 0.5 - 1 * Volume Envelope: 0.5 * Protect Voiceless Consonants: 0.5 (Disable) * Resample Audio - 0 or 48000 (Only if you need to, but it isn't necessary.) Model