RVC-Project / RVC-Project/Retrieval-based-Voice-Conversion-WebUI
How hard would it be to use human flagged audio files to train the D and G models?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 38.4k
- Forks
- 5.3k
- PR merge metrics
- No merged PRs in 30d
Description
I want to include this in my process, give the "good" files as the standard "in dir" but also have a "bad dir"
these are TTS generations humans have listened to and flagged as approved or rejected. It seems like this should boost both models.
any pointers are appreciated
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
The issue names no files, tests, or entry points. Start by locating the D and G training pipeline and how the current “in dir” data is loaded; clarify how approved and rejected audio should be represented. Done means the process can use approved files as standard input and rejected files from a separate “bad dir” for both models.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100