Repository Issue Activity (beta)

#2210 关于内存占用过大

#2851 虚拟环境下的py下载某些包，40KB的速度真慢啊

#2847 Critical bugs in train/preprocess.py, train/train.py and PyTorch 2.7+ compatibility issues (Python 3.12 branch)

#2848 Feature Request / Bug: Robotic buzzing (electric shaver sound) and VRAM overflow during Batch Inference on 3GB/low-VRAM GPUs

#2850 PART 2: Critical Argument Reversals, NumPy 1.24+ Security Breaks, and Dynamic Mel-Spectrogram Shape Mismatches in Python 3.12 Branch

#2843 tttt

#2838 Another attempt to request details regarding base model training.

#2836 关于您训练基础模型的方法，仍然有许多关键信息尚未公开，也存在不少疑问。仅凭 VCTK 并不足以解释最终模型所达到的效果，因此整个训练流程依然难以被外界理解。 能否更详细地介绍一下基础模型的训练过程，包括所使用的数据、预处理方式以及训练策略？近年来，这项技术已经取得了许多重要突破，但这部分信息始终是社区长期关注却尚未得到解答的关键问题。若能够分享更多细节，将有助于大家更好地理解并推动这一领域的发展。

#2849 unload voice

#2734 how to choosing GPU?

#2846 transformers

#2845 unload voice GPU

#2832 False Positive or real Trojan? Help

#2844 TypeError: snapshot_download() got an unexpected keyword argument 'local_dir'

#2831 add git clone into README

#2841 very bad quality of output inference

#2842 最新的main branch的人声伴奏分离，以及训练的代码都存在no module named xxx的问题

#2840 blocksize

#2839 crossfade when inference

#2837 `preprocess.py` could silently drop training data

#2835 RVC VST accessibility with screenreaders

#2834 rvc-gui为何录制声音有2个.一个是原声,一个变声

#2833 torch 2.7.1 已经下架默认源

#2567 Typo in the readme file

#2389 little typo in README.md