You need to agree to share your Hugging Face information to access this model
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
Trelis uses submitted profile information and form details to assess licensing requests and follow up; contact hello@dialt.com for correction or deletion.
Log in or Sign Up to review the conditions and access this model content.
Dialt Barge-In Detector
Detect user interruptions during AI voice-agent playback and distinguish them from backchannels that let the agent continue speaking.
| Configuration | Interruption recall | Negative-span FPR |
|---|---|---|
| Trelis/barge-in-detector | 92.22% | 10.77% |
| Silero VAD | 98.27% | 34.24% |
| VAP OTO (threshold 0.5) | 94.81% | 36.35% |
TurnBench: all 38 development conversations, 347 positives and 3,733 negative spans; fixed pipelines at different operating points, not standalone-weight performance, held-out test results or live-latency results.
Available for commercial licensing under the licence. Contact hello@dialt.com for licensing or training assistance.