Offline GPU-accelerated audio ML pipeline. faster-whisper + cross-encoder reranking + FFmpeg. Runs on 6GB VRAM.
-
Updated
Dec 26, 2025 - Python
Offline GPU-accelerated audio ML pipeline. faster-whisper + cross-encoder reranking + FFmpeg. Runs on 6GB VRAM.
Add a description, image, and links to the 6gb-vram topic page so that developers can more easily learn about it.
To associate your repository with the 6gb-vram topic, visit your repo's landing page and select "manage topics."