RVC-Project / RVC-Project/Retrieval-based-Voice-Conversion-WebUI
训练出来效果差
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 38.4k
- Forks
- 5.3k
- PR merge metrics
- No merged PRs in 30d
Description
为什么自己训练出来的模型效果那么差呢，我用20分钟的音频训练，虽然改变了声音但是跟原先的音色查不了多少啊，是因为微调过度了吗
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 report only describes a model trained on 20 minutes of audio whose output changes the voice but preserves much of the original timbre. Start by examining the training configuration and audio data referenced in the report; the issue is complete only when the cause of the poor result and a reproducible corrective change are established.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100