search

SociallyIneptWeeb / AICoverGen

A WebUI to create song covers with any RVC v2 trained AI voice from YouTube videos or audio files.
MIT License
1.02k stars 240 forks source link

Problem with onnxruntime-gpu when run webui on ubuntu #141

Open huyctdev opened 1 month ago

huyctdev commented 1 month ago

After completing install step, I run with this command python src/webui.py --listen Everything is ok but when I click to Generate button on webui, with Lisa model and a url of music video on youtube, on my terminal, it throws this message: [E:onnxruntime:Default, provider_bridge_ort.cc:1745 TryGetProviderInfo_CUDA] /onnxruntime_src/onnxruntime/core/session/provider_bridge_ort.cc:1426 onnxruntime::Provider& onnxruntime::ProviderLibrary::Get() [ONNXRuntimeError] : 1 : FAIL : Failed to load library libonnxruntime_providers_cuda.so with error: libcublasLt.so.11: cannot open shared object file: No such file or directory [W:onnxruntime:Default, onnxruntime_pybind_state.cc:895 CreateExecutionProviderInstance] Failed to create CUDAExecutionProvider. Please reference https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirementsto ensure all dependencies are met. And after that, it keep running but it's very slow because, I think it's running on my CPU, but I want it run on my GPU. How can I fix it? Thank you so much for supporting!

JackismyShephard commented 1 month ago

@huyctdev I have experienced the same issue. This seems to be due to using an invalid combination of onnx-runtime and CUDA. I have a fork of this repo here: https://github.com/JackismyShephard/ultimate-rvc. It should fix that issue, in addition to adding many new features. You can have a look at it, if you feel like it :blush: