| title: DuplexJev — speech to decisions | |
| emoji: 🎧 | |
| colorFrom: green | |
| colorTo: gray | |
| sdk: gradio | |
| sdk_version: 5.50.0 | |
| python_version: 3.10.13 | |
| app_file: app.py | |
| pinned: true | |
| license: apache-2.0 | |
| short_description: 10 voice-agent decisions from raw speech in one pass | |
| models: | |
| - adventists-ai/DuplexJev-32B-Para | |
| - adventists-ai/DuplexJev-4B-Para | |
| tags: | |
| - audio | |
| - speech | |
| - turn-taking | |
| - voice-agent | |
| - emotion-recognition | |
| DuplexJev answers every decision a voice agent needs — turn-taking, barge-in, intent, emotion, non-verbal sounds — | |
| straight from raw speech, in one forward pass. Code: https://github.com/adventists-ai/duplexjev · Paper: arXiv:2610.02638 | |