silero-vad

Enterprise-grade, lightweight pretrained voice activity detection model, widely used for speech/silence segmentation.

Link

• Visit resource

Related resources

• libfvadStandalone extraction of the WebRTC voice activity detection engine into a small, battle-tested C library.
• AudioAlignGUI research tool for aligning/synchronizing audio and video recordings of the same event captured from multiple sources.
• waveform-data.jsBBC R&D library for generating and manipulating zoomable waveform data, commonly paired with peaks.js.
• wavesurfer.jsInteractive JavaScript audio waveform player and visualization library built on HTML5/WebAudio with a plugin system.
• seewavPython CLI that renders audio waveform as an animated MP4 video via FFmpeg.
• CAMP-VQAWACV 2026 caption-embedded multimodal no-reference VQA model for compressed video, with code and HF demo.
• ffmpeg-queueFastify + Redis job queue for dispatching FFmpeg transcoding jobs, Docker Compose ready, production-used.
• PXNR No-Reference Video Quality EstimationEricsson's sample implementation of the ITU-T P.NATS phase 2 no-reference video quality estimation module.
• fssimu2Zig implementation of SSIMULACRA2 metric, ~23% faster and ~40% less memory than the reference implementation.
• BVQA_BenchmarkBlind (no-reference) VQA benchmarking toolkit comparing multiple models.