hwdsl2/docker-whisper-live
Docker image for a self-hosted WhisperLive real-time speech-to-text server, powered by faster-whisper. Provides WebSocket streaming for live audio transcription and an OpenAI-compatible REST API. Supports all Whisper models, VAD, NVIDIA GPU (CUDA) acceleration, offline mode, and multi-arch (amd64, arm64).
GitHub repository with 16 stars and 1 forks.
Language: Shell
Topics: ai, audio, automatic-speech-recognition, deep-learning, docker, docker-compose, docker-image, faster-whisper, inference, linux