集外数据测试，特别是男生，模仿效果不好
Open
- Dominant language
- Python
- Stars
- 36.9k
- Forks
- 5.2k
- PR merge metrics
- No merged PRs in 30d
Description
本人目前主要在做一句话语音克隆技术；
对你的模型做了测试，感觉集外模仿效果，特别是男生，相似度不够；
麻烦问下，这种问题怎么解决，就是单纯的增加相关预料吗？
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue names no files, tests, or entry points. Start by clarifying and reproducing the out-of-domain voice-cloning quality problem, especially for male speakers, then identify the relevant model and data-evaluation paths. Done would require an agreed cause and a defined, reproducible improvement or experiment.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100