RVC-Project / RVC-Project/Retrieval-based-Voice-Conversion-WebUI
Is it expected that v2 trained models underperform compared to v1 trained models on identical settings?
Open
Nobody has claimed this yet.
bug
help wanted
question
- Dominant language
- Python
- Stars
- 38.4k
- Forks
- 5.3k
- PR merge metrics
- No merged PRs in 30d
Description
5 minute dataset. I also used the Mangio fork which adds 'crepe' as a training option for both of these models.
Maybe for a model with a bigger dataset like 40 minutes, v2 outperforms?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the attached v1_vs_v2_Examples.zip and compare the two models trained on identical settings, including the crepe option from the Mangio fork. Reproduce the comparison with the reported five-minute dataset and determine whether the v2 result is expected or indicates a problem; document the conditions and conclusion.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100