Audio Processing with SAM Integration
11 repos
Tools and implementations for audio analysis and processing, centered around integration with Segment Anything Model (SAM) and related deep learning frameworks. The cluster includes Python libraries, Jupyter notebooks for experimentation, and specialized applications like ComfyUI plugins that bring audio segmentation and AI-powered audio understanding into creative workflows. Repos here span from core audio processing utilities to demonstration notebooks and production-ready integrations.
Python · 7
Jupyter Notebook · 2
Batchfile · 1
audio-to-audio ·8
en ·8
mlx-audio ·8
safetensors ·8
speech ·8
speech generation ·8
voice isolation ·8
