关于微调的问题
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.4k
- Forks
- 138
- PR merge metrics
- No merged PRs in 30d
Description
感谢作者更新v0.7模型，但在微调时面临一些难题：
- 我注意到其他问题中说：10min数据lora微调就可以达到一个不错的效果。请问这里作者组织训练数据的方式是带有prompt的双人对话数据形式，同时推理时保持一致的prompt对吗。但目前我自己的场景中，缺少这样的对话数据，只有个人的训练数据，请问这种情况下，我应该如何组织数据比较好。
- 在该背景下，如果全部组织为单人数据进行训练，但推理仍然使用spkid进行说话人切换，会不会导致严重错误。是否需要人为进行裁剪拼接，强行保证对话数据格式。
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 v0.7 fine-tuning and inference documentation. Done would require maintainer-confirmed guidance on organizing single-speaker data and using spkid during inference.
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