I built NOVA-VAD — a lightweight, explainable Voice Activity Detector that beats every major open...
NOVA-VAD delivers 93% accuracy on noisy audio, outperforming Silero (87%), Pyannote (62%), and WebRTC (58%). Scikit-learn engine eliminates GPU dependency—on-device inference cuts voice service cloud costs and enables retraining on proprietary datasets for compliance-bound workflows.
I built NOVA-VAD — a lightweight, explainable Voice Activity Detector that beats every major open source VAD on real-world noisy audio.
GitHub:(https://github.com/monishmal3375/nova-vad)
Benchmark (100 held-out files, never seen during training)
Model
Accuracy
What I Built Omni-VRAM is an open-source voice AI platform with 28 modules. GitHub:...
TL;DR. Trained a DoRA adapter on Qwen3-8B using 6128 personal Telegram messages. Cost: $1.50 on a...
Hello, everyone. Have you ever wanted to keep only the parts of a recording where someone is...
This is a submission for the GitHub Finish-Up-A-Thon Challenge What I Built Ovela AI...
NVIDIA releases Audex, a unified audio-text MoE LLM that adds audio generation while preserving the backbone's text reasoning
Unlike GPT-4o or Qwen3.5-Omni, Audio Interaction doesn't wait for a recording to end: it translates, transcribes, chats, and…
