Huanshere / Huanshere/VideoLingo
功能需求：希望能加入源字幕做校对的步骤
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 18.5k
- Forks
- 2k
- Avg merge
- 7h 41m
- Merged PRs (30d)
- 12
Description
主要是针对whisper 可能对一些近音词听错的情况。试了一下，一般都可以借助LLM来纠正的。但是尝试改了下，发现了问题：当前准备插入到源字幕处理完的某个步骤，但是发现VideoLingo 最后还需要和原始的音轨做字幕的同步，校正过的字幕好像就不太好同步了。
这里先提个需求讨论一下，看看有没有类似需求的。也想请教一下作者这里怎么做比较好
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 proposes adding an LLM-assisted proofreading step for source subtitles and notes that corrected subtitles may no longer synchronize with the original audio. No files, tests, or entry points are named; first map the subtitle-processing and audio-synchronization flow, then define the integration point and synchronization behavior before implementation.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- localization
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100