mirror of
https://github.com/datascale-ai/opentalking.git
synced 2026-07-03 15:22:34 +08:00
c33a43181a
Modular pipeline for text-driven talking avatars with WebRTC streaming: - FlashTalk / Wav2Lip / MuseTalk model adapters - LLM (OpenAI-compatible) → sentence split → Edge TTS → video generation - Interleaved A/V queue for lip-sync accuracy - Idle animation cache with crossfade and mouth stabilization - Unified server mode (API + worker in one process) - Immersive chat frontend (React + Tailwind + WebRTC) - Docker Compose configs for local, distributed, and Ascend 910B deployments
26 lines
581 B
Docker
26 lines
581 B
Docker
FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04
|
|
|
|
WORKDIR /app
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
python3 \
|
|
python3-pip \
|
|
python3-venv \
|
|
python-is-python3 \
|
|
ffmpeg \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
COPY pyproject.toml README.md LICENSE ./
|
|
COPY src ./src
|
|
COPY apps ./apps
|
|
COPY configs ./configs
|
|
COPY examples ./examples
|
|
COPY scripts ./scripts
|
|
|
|
RUN python -m pip install --no-cache-dir -U pip setuptools wheel \
|
|
&& python -m pip install --no-cache-dir -e ".[engine]"
|
|
|
|
EXPOSE 8765
|
|
|
|
CMD ["bash", "scripts/start_server.sh"]
|