modelscope / modelscope/ms-swift
How to train with a fixed frame using qwen2.5-omni？
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
I only see that FPS can be set as a parameter, but how do I train with a fixed frame ?
Contributor guide
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 only identifies Qwen2.5-Omni training and FPS configuration; it names no file, test, or entry point. First clarify whether fixed-frame training is already supported or requires a new option, then locate the relevant training configuration and add a focused test or documentation example showing the fixed-frame behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100