1
0
mirror of https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-06-05 17:20:25 +08:00
Commit Graph

8 Commits

Author SHA1 Message Date
源文雨
a8783c6639 optimize: some training optimizations (#95)
* optimzie(train&uvr5): rm sf & simp. AudioPre

* fix(audio): too many mallocs

* feat(audio): load_audio support stereo

* fix(audio): float32 wav saving

* fix(train): missing ckpt var
2024-11-28 03:20:14 +09:00
Zzzyt
f513f0b2e0 Fix half argument (#1683) (#1775)
* for GTX1650

* testing torch-profiler

* no more profiler & change default audio

* longer slice

* fluid container

* cache rmvpe and ui tweaks

* get my changes back after merge

* format code

* only load rmvpe when necessary

* fix rmvpe & config bug

* fix is_half again

* manual sync with upstream

* fix bool() for is_half

* revert changes for PR

* revert again

* typo

* match lower case
2024-01-30 12:51:40 +09:00
github-actions[bot]
738e55f05c chore(format): run black on dev 2024-01-26 08:09:56 +00:00
源文雨
b8bc2b6d60 drop: preprocess.py overwrite & optimize log printing 2024-01-14 16:37:55 +09:00
github-actions[bot]
322ce9b940 chore(format): run black on dev (#1697)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-01-11 22:42:26 +09:00
Zzzyt
c2ab680e18 add is_half argument to extract_feature_print.py (#1683)
* for GTX1650

* testing torch-profiler

* no more profiler & change default audio

* longer slice

* fluid container

* cache rmvpe and ui tweaks

* get my changes back after merge

* format code

* only load rmvpe when necessary

* fix rmvpe & config bug

* fix is_half again

* manual sync with upstream

* revert other changes for pull request
2024-01-11 22:40:34 +09:00
Ftps
58e32b6def format 2023-08-28 16:08:31 +09:00
Ftps
ed7b11eb49 train 1-2b 2023-08-21 20:53:11 +09:00