Enable speaker diarization for ElevenLabs Scribe #106
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…asets ElevenLabs Scribe was transcribing all speakers in multi-speaker audio (e.g., AMI meetings), while benchmarks expected only the dominant speaker. This caused artificially high WER (14.43% on AMI). Changes: - Enable diarization by default for ElevenLabs Scribe - Extract dominant speaker (most words spoken) from transcription - Fix language_code parameter (en vs eng) Results on AMI dataset (200 samples): - Before: 14.43% WER - After: 10.13% WER (30% relative improvement) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Results
AMI dataset (200 samples):
ElevenLabs Scribe was transcribing all speakers in multi-speaker audio (e.g., AMI meeting recordings), while benchmark ground truth contains only single-speaker utterances. This caused artificially high WER despite accurate transcription.