Skip to content

Conversation

@dbrkn
Copy link
Contributor

@dbrkn dbrkn commented Nov 14, 2025

This PR adds the streaming diarization pipeline used for benchmarking. It currently supports the Deepgram Streaming API, with additional pipelines to be integrated in the future.

@dbrkn dbrkn requested a review from EduardoPach November 14, 2025 22:51
@dbrkn dbrkn changed the title Add Streaming Diarization Pipeline Add Deepgram Streaming Diarization Nov 19, 2025
@EduardoPach EduardoPach changed the title Add Deepgram Streaming Diarization Add Deepgram Streaming Diarization and Speechmatics Nov 21, 2025
@dbrkn dbrkn force-pushed the berkin/streaming-diarization branch from e4b7d44 to 62870c1 Compare December 17, 2025 17:14
@dbrkn dbrkn changed the title Add Deepgram Streaming Diarization and Speechmatics Add Deepgram Streaming Diarization Dec 17, 2025
Copy link
Collaborator

@EduardoPach EduardoPach left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good, just a few nits and good to merge

@dbrkn dbrkn requested a review from EduardoPach December 31, 2025 17:20
Copy link
Collaborator

@EduardoPach EduardoPach left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

With #86, we've introduced support for forcing or hinting language to the orchestration and transcription pipelines. Could you also add it here if it has this option for streaming? Otherwise, you can warn that the hinting won't work as I did for AssemblyAITranscriptionPipeline

After that, we are good to merge.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants