bugbakery / bugbakery/audapolis
improve diarization
Open
- Dominant language
- TypeScript
- Stars
- 1.9k
- Forks
- 62
- PR merge metrics
- No merged PRs in 30d
Description
First test of audapolis with the German (big) language model. While the transcription is remarkably accurate, the speaker diarization is not plausible, since it splits the same speaker into many with very small segments of text.
It also seems to detect new "speakers" who do not actually say something (Speaker 7 in the screenshot).
Any ideas about what could be done to improve diarization / speaker detection?
Contributor guide
Assessment
This issue has not been assessed yet.