RVC-Project / RVC-Project/Retrieval-based-Voice-Conversion-WebUI
有什麼建議的訓練指南 & index file的疑問?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 38.4k
- Forks
- 5.3k
- PR merge metrics
- No merged PRs in 30d
Description
我準備的所有訓練素材大約時長兩小時左右(唱歌的一小時 說話的一小時)
當我把所有訓練素材(說話+唱歌)拿去訓練index檔時 訓練好的index檔只有30MB的大小
但是當我將訓練素材裡說話素材去除 只留下唱歌素材 然後再拿去訓練index檔 訓練出的index檔大小卻400MB左右
我後續也將這兩個模型訓練完成 並分別拿去推理同一首歌 聽起來卻是30MB的那個更好、更像 所以index file的大小很大代表什麼?
其實我就是好奇index file大小的意義是什麼 理論上是400MB比較好還是30MB的那個?
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
No file, test, or entry point is named. Start by locating the training and index-generation workflow in the repository, then document what index size represents and whether either result is preferable, using the reported speech-and-singing versus singing-only results as examples.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100