Model not using GPU (RTX 3060 Ti), running on CPU

[Geeky-Yogesh]

I am using Kitten TTS on a system with an NVIDIA GeForce RTX 3060 Ti, but the model runs on CPU instead of GPU.

System Info

OS: Ubuntu
GPU: RTX 3060 Ti
Python: 3.12.2

Checks

import torch
print(torch.cuda.is_available())

GPU is detected (nvidia-smi works), but model still runs on CPU.

Expected
Model should use CUDA (GPU).

Request
Is GPU inference supported? If yes, how can I enable it?

[NafQan]

This is an onnx model, install onnxruntime-gpu if you want to run it on a gpu