hwdsl2/scribecrate-live

ScribeCrate Live: self-hosted real-time transcription server powered by WhisperLive and faster-whisper. WebSocket transcription and speech-to-English translation, plus an OpenAI-compatible REST API for file transcription. All Whisper models, VAD, and offline mode with cached models. Docker on CPU (amd64/arm64) or NVIDIA GPU (CUDA, amd64).

语言：Shell · GitHub 星标：38 · Fork：5

话题：ai · audio · automatic-speech-recognition · cuda · docker · docker-compose · docker-image · faster-whisper

在 GitHub 上查看原仓库