[Documentation]: How to generate SRT/VTT transcripts
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 1.9k
- Forks
- 152
- Avg merge
- 4h 14m
- Merged PRs (30d)
- 11
Description
Description of errors
Sorry if this isn't the right place to ask this. The GitHub repository description says the project supports SRT/VTT for Whisper, but the documentation doesn't mention it, I couldn't find any reference to it anywhere else online, and https://lemonade-server.ai/docs/api/openai/ says Lemonade refuses to generate SRT/VTT files when using FastFlowLM as a backend because "FLM returns no segment timestamps".
I had a quick look at the source code and Whisper::generate() has a return_timestamps parameter, which runner.cpp hardcodes to false when invoking it.
Is there some other way of generating timed transcripts? Is that functionality still in testing?
Attach any links, screenshots, or additional evidence you think will be helpful.
No response
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 with Whisper::generate() and the call in runner.cpp, where return_timestamps is hardcoded to false; compare that behavior with the OpenAI API documentation linked in the issue. Determine whether SRT/VTT generation is supported with FastFlowLM, and document the supported procedure or the limitation clearly.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- documentation
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100