RVC-Project/Retrieval-based-Voice-Conversion-WebUI

error rvc

Open

#1,957 创建于 2024年4月9日

在 GitHub 查看
 (1 评论) (0 反应) (0 负责人)Python (18,427 star) (2,849 fork)batch import
bughelp wanted

描述

Traceback (most recent call last): File "C:\Users\Utilizador\Desktop\RVC-GUI-pkg-20220525-mp3fix\RVC-GUI-pkg\rvcgui.py", line 129, in vc_single audio_opt = vc.pipeline( File "C:\Users\Utilizador\Desktop\RVC-GUI-pkg-20220525-mp3fix\RVC-GUI-pkg\vc_infer_pipeline.py", line 326, in pipeline sid = torch.tensor(sid, device=self.device).unsqueeze(0).long() RuntimeError: CUDA error: the launch timed out and was terminated CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

贡献者指南

技术栈
pythonpytorch
领域
machine learningai
议题类型
bug
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
1-3 hours
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
fresh
清晰度议题是否清楚说明期望改动、验收标准和下一步。
needs investigation
前置要求
PythonPyTorchCUDARVC pipeline basics
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
20
研究方向
Investigate the CUDA timeout error in vc infer pipeline.py line 326. First, reproduce the error with the given traceback. Check if the issue is environment specific by verifying CUDA drivers, GPU memory, and PyTorch version. Try adding CUDA LAUNCH BLOCKING=1 as suggested in the error message. Consider reducing the batch size or input length to avoid GPU timeout. Look for existing discussions in the repository issues or pull requests that address similar CUDA errors. If no clear solution, ask the reporter for system details and steps to reproduce.