5 Commits

Author SHA1 Message Date
RVC-Boss
81eed5e8f6 更新多说话人训练webui,提供cli命令 / Update the multi-speaker training WebUI and provide CLI commands 2026-08-04 15:47:05 +08:00
RVC-Boss
132126af72 Replace UVR5 separation backend with pymss
Add the five-model MSST backend, CUDA precision reuse, fast MP3/M4A encoding, PyAV compatibility fixes, remote dependencies, model configs, Hugging Face download guidance, and multilingual pymss credits. Remove the obsolete tools/uvr5 implementation.
2026-07-23 01:40:12 +08:00
RVC-Boss
54465d6519 Use GPU processing for UVR5 and input audio loading and resampling where possible to improve inference efficiency and reduce CPU usage 2026-07-21 21:23:25 +08:00
RVC-Boss
b3f54df1be Add CUDA Graph inference acceleration support 2026-07-20 22:34:58 +08:00
RVC-Boss
5d47da1488 Import RVC 20260716 Nvidia 50x0 v2bb 2026-07-19 21:19:30 +08:00