modelscope / modelscope/FunASR
我又来了, 还是中文断句继续优化的样本
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 20.4k
- Forks
- 2k
- Avg merge
- 4h 55m
- Merged PRs (30d)
- 169
Description
样本音频：
http://devv.cc:8999/mp3/从仲树看知识囤积癖_%23仲树_%23原生家庭_%23东亚文化.mp3
下载命令:
curl -O http://devv.cc:8999/mp3/从仲树看知识囤积癖_%23仲树_%23原生家庭_%23东亚文化.mp3
funasr 1.4.14
红色为字幕句间隙少于100ms的，按说这么小的间隙，没有充分的理由或特殊权重，是没有理由硬断的，它不识别 ”汉娜＊阿伦特“ 和 “欧叶尼*葛郎台” 也就罢了。是否这些地方刚好位于分批或分段”喂料“ 的边界上？或者说：在这种特殊的字幕生成（transcription）工作模式下，喂入边界的方式是否就不应该存在？技术上应该有办法避开简陋的固定时长硬截段的方式吧？
图中的字幕起－止时间后的“60”是当前末与下句起始时间之间的gap时长。
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
Start by downloading the linked sample audio with the provided curl command and reproducing the subtitle gaps using FunASR 1.4.14. Trace how transcription input is divided into batches or segments, then compare the reported Chinese sentence breaks around the named terms. Done should include a reproducible test or sample demonstrating that unjustified short-gap breaks are avoided.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 45/100