whisper_pipeline/dockerfile

# Use nvidia/cuda as base image with Python
FROM nvidia/cuda:12.2.2-cudnn8-runtime-ubuntu22.04

# Use args
ARG USE_CUDA
ARG USE_CUDA_VER

## Basis ##
ENV ENV=prod \
    PORT=8000 \
    USE_CUDA_DOCKER=${USE_CUDA} \
    USE_CUDA_DOCKER_VER=${USE_CUDA_VER}

# Install GCC and build tools
RUN apt-get update && \
    apt-get install -y gcc build-essential curl git pkg-config libicu-dev && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/*

RUN apt-get update -y && apt-get install -y python3-pip



# Set working directory
WORKDIR /app

# Copy the requirements.txt file and install dependencies
COPY ./requirements.txt .

# Install dependencies
RUN pip install uv && \
    if [ "$USE_CUDA" = "true" ]; then \
        pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$USE_CUDA_DOCKER_VER --no-cache-dir; \
    else \
        pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir; \
    fi

# Copy faster-whisper-main folder and install
COPY ./faster-whisper-main ./faster-whisper-main
RUN pip install ./faster-whisper-main --no-cache-dir

RUN pip install --no-cache-dir -r requirements.txt


# Copy the remaining application code
COPY . .

# Expose the API port
EXPOSE 8000

# Set the environment variables
ENV HOST="0.0.0.0"
ENV PORT="8000"

# Set entrypoint to run the FastAPI server
ENTRYPOINT ["bash", "start.sh"]