Exceptionally high quality model <a:Heart_eye:1147246308000796763>

Trained on 90 minutes of clean audio direct from game files. Works exceptionally well on female pop singers like Olivia Rodrigo (though won't reach her full vocal range). If you want best outcome for any songs with quite high belting I would suggest lowering by 2-3 semitones. I tried 500 Epochs but it didn't sound quite as great as 450. I kept lower ones just in case anyone reports any issues back and I can edit with 300 Epochs~

<https://huggingface.co/datasets/pentyb/ShadowheartRVCv2/blob/main/Shadowheart.zip>

If you use this please credit @ pentybeats on YouTube! <https://www.youtube.com/@pentybeats>

Shadowheart's strong enunciation comes through quite well, especially if your vocal is clean and of high quality.

Sound attached: *the grudge by olivia rodrigo*
Shadowheart settings: feature ratio 0.87 / rvmpe+ / min hz raised to 60hz and max hz upped to 1500hz)

Will post more demos later tonight!

Additional Details:

Tags: Fictional Character, RVC v2, English

Related URL: https://huggingface.co/datasets/pentyb/ShadowheartRVCv2/blob/main/Shadowheart.zip%3E

Related URL: https://youtube.com/@pentybeats%3E

Download Link: https://huggingface.co/datasets/pentyb/ShadowheartRVCv2/resolve/main/Shadowheart.zip?download=true Hosted on Hugging Face

Convert this model in EasyAIVoice

Original Link: https://huggingface.co/datasets/pentyb/ShadowheartRVCv2/blob/main/Shadowheart.zip (404 not found)

Auto-resolved Link: https://huggingface.co/datasets/pentyb/ShadowheartRVCv2/resolve/main/Shadowheart.zip?download=true