Skip to content

Add request merging to prevent fragmented speech recognition#442

Merged
uezo merged 1 commit intomasterfrom
develop
Aug 10, 2025
Merged

Add request merging to prevent fragmented speech recognition#442
uezo merged 1 commit intomasterfrom
develop

Conversation

@uezo
Copy link
Owner

@uezo uezo commented Aug 10, 2025

  • Merge multiple consecutive requests within mergeRequestThreshold timeframe
  • Prevents conversation breakdown when user speech is recognized in fragments
  • Improves conversation continuity and user experience

To enable this feature, set mergeRequestThreshold in DialogProcessor to a value greater than 0 on inspector. When a new request arrives within the specified seconds after the previous request, they will be merged into a single request.

- Merge multiple consecutive requests within `mergeRequestThreshold` timeframe
- Prevents conversation breakdown when user speech is recognized in fragments
- Improves conversation continuity and user experience

To enable this feature, set `mergeRequestThreshold` in `DialogProcessor` to a value greater than 0 on inspector. When a new request arrives within the specified seconds after the previous request, they will be merged into a single request.
@uezo uezo merged commit 396a9d0 into master Aug 10, 2025
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.

1 participant