Motorola Notification (RVC v2) - 1000 epochs

[formal locust]

its not possible to do the perfect motorola notification model. please don't take down for poor quality!

image upscaled using realesrgan pytorch.

trained on a 0:01-second dataset ripped directly from YT. (rx de-click, resample + eq, renegate noise-gate)

pitch extraction: rmvpe
steps: 2k
batch size: 8
pretrain: original v2 / 32k
precision: fp32

i recommend setting the search feature/index ratio to 1.

link - https://huggingface.co/FurnTheFurnace/RVCModels/resolve/main/Motorola-Notification_1000e_2000s.zip?download=true

please don't forget to credit me when you use this model.

[fleet hare]

Rate the model

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

[formal locust]

originally this was going to be trained to 1500 epochs, but i trained it to 1000 instead because it was overtraining.

[formal locust]

*not using fp32 anymore, it isn't worth it at all. realized just now.

[nocturne depot]

Model Ready ✅

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