Pitch previews
Listen across generated pitch samples, then Run. Hold Ctrl or Cmd to select multiple pitches.
This model is around 23 minutes of mainly Karaoke/Live vocals. I may look into trying the Future Nostalgia model again. Talking model is from interviews, which is around 9 minutes.
Singing Model: (150-300 Epochs) https://huggingface.co/AI-Wheelz/DUA-LIVE-RVCv2/resolve/main/DUA-LIVE-RVCv2.zip
Talking Model: (500 Epochs) https://huggingface.co/AI-Wheelz/DUATALKS_RVCv2/resolve/main/DUA-TALK-RVCv2.zip
I would recommend you play around with the RVC settings to get the right tone and sound out.
Tags: TTS / Realtime, E-Celeb, Artist, RVC v2, English
Related URL: https://huggingface.co/AI-Wheelz/DUA-LIVE-RVCv2/resolve/main/DUA-LIVE-RVCv2.zip
Related URL: https://huggingface.co/AI-Wheelz/DUATALKS_RVCv2/resolve/main/DUA-TALK-RVCv2.zip
Download Link: https://huggingface.co/AI-Wheelz/DUA-LIVE-RVCv2/resolve/main/DUA-LIVE-RVCv2.zip Hosted on Hugging Face
Convert this model in EasyAIVoice
Listen across generated pitch samples, then Run. Hold Ctrl or Cmd to select multiple pitches.