Riko Solari [VSPO!] | RMVPE | 146 Epochs

[peak gale]

Huh even though there is a decent amount noise in the dataset (and in the inference audio) the model didnt turn out to bad.

Info:

• Batch Size: 6
• Dataset Length: 30 Minutes
• Pretrain: Default
• Precision: FP32
• Sample Rate: 32K

Please credit me if used 🙂

📥 Download: https://huggingface.co/Razer112/Public_Models/resolve/main/Riko_Solari.zip?download=true

[thorny herald]

Rate the model

To rate this model, either use /rate or click the buttons below.

[onyx gust]

as long the noise present is the same both inside the voice and out of it, rvc identifies it as a voice feature and can learn both the voice and the noise without problems
thanks to the vctk dataset rvc is robust to noise + you used rmvpe which also robust to noise
so thats why it came out good despite having noise

[tawny belfry]

Model Ready ✅

This model has been synced with Weights and is ready to use for free!