zuoer
Domain-neutral run segmenter: the Silero-derived hysteresis state machine that turns any frame-probability sequence into contiguous runs with mean/peak aggregates — one instance per class for sound-event detection. Over it sits a backend-agnostic voice-activity-detection (VAD) shell: the VadBackend seam and the Speech* names. The model, inference runtime, and audio I/O live in the backend crate.
View on Github
Activity
- Latest release
- 3d ago
- Total releases
- 5
- Cadence
- ~10 days
- Last 12 months
- 5
Reach
- Downloads
- 2.9k
- Stars
- 0
Details
- License
- MIT OR Apache-2.0
- First release
- Jul 18, 2026
Releases
| Version | Released | |
|---|---|---|
0.3.2
patch
| ||
0.3.1
patch
| ||
0.3.0
minor
| ||
0.2.0
minor
| ||
0.1.0
unknown
|