[GH-ISSUE #267] [Feature request] Automatic batch processing of long files on harvest for limited RAM machines #130

New issue

Open

opened 2026-10-20 09:55:38 +00:00 by bsakaguchi · 4 comments

bsakaguchi commented

2026-10-20 09:55:38 +00:00

Owner

Originally created by @kalomaze on GitHub (May 10, 2023).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/267

A common complaint from Google Colab users is harvest being unusable without manually splitting their song into parts. I wonder if an argument in the command to run python infer-web.py could be used to forcefully do it in batches so that it still exports without erroring out? If not that, splitting the song into ~30s intervals that cut off at silence and then stitching them together to serve a complete wav?

Originally created by @kalomaze on GitHub (May 10, 2023). Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/267 A common complaint from Google Colab users is harvest being unusable without manually splitting their song into parts. I wonder if an argument in the command to run python infer-web.py could be used to forcefully do it in batches so that it still exports without erroring out? If not that, splitting the song into ~30s intervals that cut off at silence and then stitching them together to serve a complete wav?

bsakaguchi added the

help wanted

enhancement

labels

2026-10-20 09:55:38 +00:00

bsakaguchi commented

2026-10-20 09:55:39 +00:00

Author

Owner

@RVC-Boss commented on GitHub (May 10, 2023):

decrease "Number of CPU threads to use for pitch extraction"

@RVC-Boss commented on GitHub (May 10, 2023): decrease "Number of CPU threads to use for pitch extraction"

bsakaguchi commented

2026-10-20 09:55:39 +00:00

Author

Owner

@kalomaze commented on GitHub (May 10, 2023):

This is specifically for inferencing. It will time out/error with a song longer than a minute and a half (on a Google Colab)
Also, I notice some users who already 'split up' their inference file in parts to help increase the quality by having less to process at once. This could be helpful for automating that, and also avoiding the bug where parts of the audio will be very quiet after long silence periods in the vocals. The biggest problem, I'm guessing, is finding where silence begins and ends to make good 'cut' points.

@kalomaze commented on GitHub (May 10, 2023): This is specifically for inferencing. It will time out/error with a song longer than a minute and a half (on a Google Colab) Also, I notice some users who already 'split up' their inference file in parts to help increase the quality by having less to process at once. This could be helpful for automating that, and also avoiding the bug where parts of the audio will be very quiet after long silence periods in the vocals. The biggest problem, I'm guessing, is finding where silence begins and ends to make good 'cut' points.

bsakaguchi commented

2026-10-20 09:55:39 +00:00

Author

Owner

@Mangio621 commented on GitHub (May 11, 2023):

Soon to be working on an 'inference batcher script' soon on my fork at https://github.com/Mangio621/Mangio-RVC-Fork

@Mangio621 commented on GitHub (May 11, 2023): Soon to be working on an 'inference batcher script' soon on my fork at https://github.com/Mangio621/Mangio-RVC-Fork ![image](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/assets/42698330/2fc4406e-ea06-44ca-95d1-80d66a65e25f)

bsakaguchi commented

2026-10-20 09:55:39 +00:00

Author

Owner

@aracap commented on GitHub (May 13, 2023):

can we also limit RAM usage when splitting audio ? for example limit RAM to 12 GB since colab free version limit is 12 GB

@aracap commented on GitHub (May 13, 2023): can we also limit RAM usage when splitting audio ? for example limit RAM to 12 GB since colab free version limit is 12 GB