not the best quality, but sounds ok.
trained on 14 minutes of her speaking from her stream
pitch extraction: rmvpe
steps: 16.3k - 16.4k
batch size: 7
pretrain: regular v2
huggingface: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/memory.zip
Tags: No tags available
Download Link: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/memory.zip