Dockerfile

FROM nvidia/cuda:12.9.0-devel-ubuntu24.04

# Avoid interactive prompts during package installation
ENV DEBIAN_FRONTEND=noninteractive

# Install Python and system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3 \
    python3-pip \
    python3-dev \
    git \
    gcc \
    g++ \
    libsndfile1 \
    ffmpeg \
    && rm -rf /var/lib/apt/lists/*

# Set Python alias (Ubuntu 24.04 ships Python 3.12)
RUN ln -sf /usr/bin/python3 /usr/bin/python

# Allow pip to install packages system-wide in the container (PEP 668)
ENV PIP_BREAK_SYSTEM_PACKAGES=1

# Set working directory
WORKDIR /app

# Install PyTorch ecosystem (cu128 wheels for CUDA 12.8+/12.9 compat)
RUN pip install --no-cache-dir \
    torch==2.8.0 \
    torchaudio==2.8.0 \
    --index-url https://download.pytorch.org/whl/cu128

# Install core dependencies
RUN pip install --no-cache-dir \
    transformers==4.51.0 \
    accelerate \
    huggingface-hub \
    soundfile

# Install common eval dependencies
# Pin datasets to 2.19.0 to avoid torchcodec dependency in newer versions
RUN pip install --no-cache-dir \
    evaluate \
    datasets==2.19.0 \
    librosa \
    jiwer \
    packaging \
    num2words \
    peft

# Force soundfile backend for datasets audio decoding
ENV HF_AUDIO_DECODER_BACKEND=soundfile

RUN pip install --no-cache-dir --upgrade "kaldialign>=0.12.0" \
    && python -c "from kaldialign import batch_error_rate; print('kaldialign OK')"

# Copy the full repository
COPY . /app

# Default entrypoint
ENTRYPOINT ["bash"]

EXPOSE 7860
CMD ["-c", "python3 -m http.server 7860"]