kalomaze

This would solve the problem of coming across a channel that formats their song uploads as Song - Artist rather than Artist - Song, I have to manually correct these...

More dynamic volume range in future generations?

2

When pre-processing the wavs, they are all normalized to keep the dataset even and consistent. This makes sense to me as a method to ensure data processed is relatively similar,...

[Feature request] Automatic batch processing of long files on harvest for limited RAM machines

4

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...

Standard for most of recorded music is 44khz instead of 40khz

2

I've been told contentvec hubert was trained at 44khz, but there are 3 options in RVC for 40khz, 48khz, and 32khz. This confuses me, as the standard for most recorded...

2333333 steps pth files issue

1

There seems to be a bug where pth files will a lot of the times save with this number of steps in the filename, which can be confusing and misleading....

I totally understand if this is out of the scope of RVC as a project in general, and I don't have the technical qualifications to say if it would be...

Is it expected that v2 trained models underperform compared to v1 trained models on identical settings?

6

[v1_vs_v2_Examples.zip](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/files/11490148/v1_vs_v2_Examples.zip) 5 minute dataset. I also used the [Mangio fork which adds 'crepe' as a training option](https://github.com/Mangio621/Mangio-RVC-Fork) for both of these models. Maybe for a model with a bigger dataset...

Default index ratio increased again in latest release - negatively impacting performance for little to no gain?

3

I noticed that the default value seems to have changed again. I would like to know the reasoning because despite messing with the other option for voiceless consonant and crepe...

10% of audio data is duplicated during preprocessing

4

https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/assets/66376113/ccc991bc-f614-4753-a533-ab0afdd017cf If you check the preprocessed wavs folder before doing feature extract, you can notice that they are not properly aligned when put up next to each other back to...