# docker/Dockerfile.rocm
#
# WhisperLive faster_whisper backend on AMD ROCm GPUs.
# Uses the official CTranslate2 ROCm wheel (ships kernels for gfx803 through
# gfx1201 including Strix Halo gfx1151 and RDNA4 gfx1200/1201).
#
# Build:
#   docker build -f docker/Dockerfile.rocm -t whisperlive-rocm .
#
# Run (expose the WebSocket port; add --enable_rest --rest_port 8000 -p 8000:8000 for REST):
#   docker run --rm -it \
#       --device=/dev/kfd --device=/dev/dri \
#       --group-add "$(getent group video | cut -d: -f3)" \
#       --group-add "$(getent group render | cut -d: -f3)" \
#       -p 9090:9090 whisperlive-rocm

FROM rocm/pytorch:rocm7.2.4_ubuntu24.04_py3.12_pytorch_release_2.10.0

ARG DEBIAN_FRONTEND=noninteractive
ARG CT2_WHEEL_URL=https://github.com/OpenNMT/CTranslate2/releases/download/v4.8.0/rocm-python-wheels-Linux.zip

RUN apt-get update -qq && \
    apt-get install -y --no-install-recommends curl unzip portaudio19-dev && \
    apt-get clean && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Install the CTranslate2 ROCm wheel (official release artifact).
# This replaces any CUDA-only ctranslate2 and enables GPU on AMD.
RUN curl -sL "${CT2_WHEEL_URL}" -o /tmp/ct2-rocm.zip && \
    unzip -j /tmp/ct2-rocm.zip 'temp-linux/ctranslate2-*-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl' -d /tmp && \
    pip install --no-cache-dir --force-reinstall /tmp/ctranslate2-*-cp312-*.whl && \
    rm -f /tmp/ct2-rocm.zip /tmp/ctranslate2-*.whl

# Install server requirements
COPY requirements/server.txt /app/
RUN pip install --no-cache-dir -r server.txt && rm server.txt

COPY whisper_live /app/whisper_live
COPY run_server.py /app

EXPOSE 9090

CMD ["python", "run_server.py", "--port", "9090", "--backend", "faster_whisper"]