I-IAL9000/shrinkerr v0.9.81

on GitHub

Added

• GPU-accelerated audio detection on the :nvenc image, plus medium/large-v3 models. The nvenc image now ships cuDNN so faster-whisper runs on the GPU (device="auto", falls back to CPU), and the Settings dropdown exposes medium and large-v3 — making reliable detection of low-resource languages (e.g. Icelandic) practical. Default model unchanged (tiny).

Docker images

Pinned to this release:

docker pull ghcr.io/i-ial9000/shrinkerr:v0.9.81         # portable (amd64 + arm64, CPU)
docker pull ghcr.io/i-ial9000/shrinkerr:v0.9.81-nvenc   # x86_64 + NVIDIA GPU (NVENC)
docker pull ghcr.io/i-ial9000/shrinkerr:v0.9.81-edge    # as above but ffmpeg master
docker pull ghcr.io/i-ial9000/shrinkerr:v0.9.81-edge-nvenc

Floating tags (:latest, :edge, :nvenc, :edge-nvenc) track the most recent release of each lineage.