microsoft / microsoft/foundry-local
Foundry Local Whipser - does NOT include word-level or segment-level timestamps i
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 2.6k
- Forks
- 369
- Avg merge
- 2d 17h
- Merged PRs (30d)
- 39
Description
Can you confrm that the Microsoft.AI.Foundry.Local SDK's Whisper implementation does NOT include word-level or segment-level timestamps in its current version. The SDK returns only the transcribed text.
Formats I would like
Is this a limitation of the current SDK version?
Here is a sample Poc Using JSON and TEXT transcription output:
Foundry Local C# Sample Scenario
https://github.com/leestott/FLWhisper
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
Review the Microsoft.AI.Foundry.Local Whisper SDK behavior and the linked C# sample at https://github.com/leestott/FLWhisper, comparing its JSON and text transcription output with the requested formats. Done means confirming whether the current SDK exposes word-level or segment-level timestamps, or defining the scope for adding that support.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, csharp
- Domain
- ai, audio-video-rtc
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 38/100