modelscope / modelscope/FunASR
建议给一个 roadmap
Open
@qiulang is already working on this.
Since Jul 13, 2026.
documentation
enhancement
help wanted
needs feedback
question
ready for PR
- Dominant language
- Python
- Stars
- 20.4k
- Forks
- 2k
- Avg merge
- 4h 55m
- Merged PRs (30d)
- 169
Description
我读完 community_growth_20k.md 我觉得应该再有一个 roadmap， 制定下一步的发展方向，甚至包括哪些 help wanted .
另外有个小问题，我好像以前也问过，但是看了 community_growth_20k 也没搞懂，就是 FunAudioLLM/Fun-ASR 这个项目的作用, 我能理解 FunAudioLLM 要强调 LLM-ASR model， 但还是搞不太清和 modelscope/FunASR 分工在哪里；另外如果作为使用者，需要知道 FunAudioLLM/Fun-ASR 这个项目吗？
| Repository | Role in the ecosystem | Growth surface |
|---|---|---|
| modelscope/FunASR | Core toolkit, Python package, runtime services, deployment docs | First-run success, production deployment, issue/PR operations |
| FunAudioLLM/Fun-ASR | Fun-ASR-Nano model family and LLM-ASR identity | Model cards, Transformers integration, benchmarks, vLLM/GGUF stories |
我们关于 Fun-ASR-Nano 问题讨论也都是在 modelscope/FunASR 里不是在 FunAudioLLM/Fun-ASR | Fun-ASR-Nano
然后我读 modelscope/FunASR 的 serve_realtime_ws.py 和 FunAudioLLM的 serve_realtime_ws.py 觉得它们基本一样，但差异的地方又让人糊涂， 比如 modelscope/FunASR 有 get_partial_decode_audio 但 FunAudioLLM 的 没有，可是 get_partial_decode_audio 我们也讨论过几次，为什么 会一个有一个没有？
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.
Assessment
This issue has not been assessed yet.