faster-whisper lscr.io/linuxserver/faster-whisper https://github.com/orgs/linuxserver/packages/container/package/faster-whisper Donations https://www.linuxserver.io/donate https://raw.githubusercontent.com/linuxserver/docker-templates/master/linuxserver.io/img/donate.png bridge false https://github.com/linuxserver/docker-faster-whisper/issues/new/choose bash https://github.com/linuxserver/docker-faster-whisper#application-setup https://github.com/linuxserver/docker-faster-whisper#readme latest Stable releases gpu Releases with Nvidia GPU support (amd64 only) https://github.com/linuxserver/docker-faster-whisper/tree/gpu#readme https://github.com/linuxserver/docker-faster-whisper/tree/gpu#application-setup gpu-legacy Legacy releases with Nvidia GPU support for pre-Turing cards (amd64 only) https://github.com/linuxserver/docker-faster-whisper/tree/gpu-legacy#readme https://github.com/linuxserver/docker-faster-whisper/tree/gpu-legacy#application-setup https://github.com/SYSTRAN/faster-whisper Faster-whisper(https://github.com/SYSTRAN/faster-whisper) is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This container provides a Wyoming protocol server for faster-whisper. https://raw.githubusercontent.com/linuxserver/templates/main/unraid/faster-whisper.xml https://raw.githubusercontent.com/linuxserver/docker-templates/master/linuxserver.io/img/linuxserver-ls-logo.png 2026-01-26 ### 2026-01-26 - Default to `auto` for model and language if not set. ### 2025-08-20 - Add gpu-legacy branch for pre-Turing cards. ### 2025-08-10 - Add support for local-only mode. ### 2024-12-30 - Add arm64 support for non-GPU builds. ### 2024-12-05 - Build from Github releases rather than Pypi. ### 2024-07-18 - Rebase to Ubuntu Noble. ### 2024-05-19 - Bump CUDA to 12 on GPU branch. ### 2024-01-08 - Add GPU branch. ### 2023-11-25 - Initial Release.