-
Notifications
You must be signed in to change notification settings - Fork 3
Add Deepgram Streaming Diarization #74
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
e4b7d44 to
62870c1
Compare
EduardoPach
left a comment
There was a problem hiding this 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
| elif "model_timestamps_confirmed" in output and output["model_timestamps_confirmed"]: | ||
| # Fallback to regular transcription without speaker | ||
| for timestamp_group in output["model_timestamps_confirmed"]: | ||
| for word_info in timestamp_group: | ||
| if "word" in word_info: | ||
| words.append( | ||
| Word( | ||
| word=word_info.get("word", ""), | ||
| start=word_info.get("start"), | ||
| end=word_info.get("end"), | ||
| speaker=None, | ||
| ) | ||
| ) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Setting the speaker to None will likely cause an error downstream. I'd suggest raising an error in this case since the main reason speaker labels is the core info for Orchestration
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.