Skip to content

Conversation

@boazsender
Copy link
Contributor

Adds sentence retrieval from Assembly as a backup for when speaker diarisation doesn't complete (more than 10 speakers) and no utterances are returned.

@vercel
Copy link

vercel bot commented May 29, 2025

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
maple-dev ✅ Ready (Inspect) Visit Preview 💬 Add feedback Jun 12, 2025 3:55pm

Copy link
Collaborator

@Mephistic Mephistic left a comment

Choose a reason for hiding this comment

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

LGTM, just the note about which AssemblyAI extract method to use. 👍 to doing this for all hearings to start, even those with acceptable diarization - we can always disable this conditionally if we find we're not getting enough value.

// If there is one authenticated event, pull out the parts we want to
// save and try to save them in the db.

const { sentences } = await assembly.transcripts.sentences(
Copy link
Collaborator

Choose a reason for hiding this comment

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

Just checked with Matt V - we'd prefer to use the extract paragraphs API rather than the extract sentences API - sentences can get pretty fragmented in some cases, especially around bill names.

@Mephistic Mephistic merged commit a31fef3 into codeforboston:main Jun 18, 2025
7 checks passed
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.

2 participants