Generated audio is noisy and jittered when running via Gradio

[beautifulchoi]

Hello, and thank you for your amazing work on making this fully open-source!

While testing Stable Audio through Gradio, I encountered an issue: every time I run the model — both with a prompt and without one — the generated audio turns out extremely noisy and jittered.

Do you have any idea what might be causing this issue, or any suggestions for how to fix it?
I’d really appreciate any guidance.

Thanks again for your great work!

I'm using torch 2.5.1 with torchaudio 2.9.0, torchcodec 0.8.1