I-IAL9000/shrinkerr v0.9.18

on GitHub

Added

• Language-detection tuning in Settings → Video. The audio detection model (tiny/base/small) and the audio/subtitle confidence thresholds are now UI settings instead of env-only. Defaults unchanged (tiny / 0.6 / 0.7); the model reloads live on change (no restart). The SHRINKERR_* env vars still work and override the UI values.

Docker images

Pinned to this release:

docker pull ghcr.io/i-ial9000/shrinkerr:0.9.18         # portable (amd64 + arm64, CPU)
docker pull ghcr.io/i-ial9000/shrinkerr:0.9.18-nvenc   # x86_64 + NVIDIA GPU (NVENC)
docker pull ghcr.io/i-ial9000/shrinkerr:0.9.18-edge    # as above but ffmpeg master
docker pull ghcr.io/i-ial9000/shrinkerr:0.9.18-edge-nvenc

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