Measure how much of a mix's timeline is covered by a given vocal stem — raw vocal-presence signal for remix/instrumental analysis. MIT.
-
Updated
Jul 16, 2026 - Python
#
vocal-detection
Here are 2 public repositories matching this topic...
Frame-level shouting detection for music/speech using librosa features and a PyTorch Lightning CNN. Includes training, inference, visualization tools, Docker support, and diagnostics for inspecting labels and class balance.
docker deep-learning pytorch tensorboard mps speech-processing audio-processing computer-audio pytorc-lightning vocal-detection
-
Updated
Nov 13, 2025 - Python
Improve this page
Add a description, image, and links to the vocal-detection topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the vocal-detection topic, visit your repo's landing page and select "manage topics."