Default models work for me, downloaded models don't

[Glazedhamster]

Issue Type

Question

vc client version number

MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.11

OS

Win 10

GPU

Radeon RX 6600

Clear setting

yes

Sample model

yes

Input chunk num

yes

Wait for a while

The GUI successfully launched.

read tutorial

yes

Extract files to a new folder.

yes

Voice Changer type

RVC

Model type

pyTorch

Situation

The default voices work well, but every model I download sounds very choppy and delayed. Furthermore, the res value just builds up well into 5 digits of ms when trying to use those models. Any idea what I might be doing wrong here?

[w-okada]

download model is pytorch model. AMD GPU is supported only for onnx model. Convert the model to onnx. How to convert is described in tutorial.

[Glazedhamster]

download model is pytorch model. AMD GPU is supported only for onnx model. Convert the model to onnx. How to convert is described in tutorial.

Works like a charm now. Many thanks!