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

# Avoid interactive prompts during package installation
ENV DEBIAN_FRONTEND=noninteractive

# Install Python and system dependencies
# Ubuntu 24.04 ships FFmpeg 6.1 (torchcodec requires FFmpeg 5+, <8)
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3 \
    python3-pip \
    python3-dev \
    git \
    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)
# torchvision is required by Qwen3-Omni's AutoProcessor, which wraps a video processor
# (Qwen2VLVideoProcessor) even when only text/audio inputs are used.
RUN pip install --no-cache-dir \
    torch==2.8.0 \
    torchaudio==2.8.0 \
    torchvision==0.23.0 \
    torchcodec==0.6.0 \
    --index-url https://download.pytorch.org/whl/cu128

# Install common requirements (torch already installed above, pip will skip it)
# regex + kaldialign are required by the Open ASR Leaderboard `normalizer/` used for WER scoring.
# zhconv folds traditional Chinese to simplified for the CER scoring path (Seed-TTS zh splits).
RUN pip install --no-cache-dir \
    git+https://github.com/huggingface/transformers.git \
    evaluate \
    datasets \
    librosa \
    jiwer \
    num2words \
    regex \
    kaldialign \
    zhconv \
    sentencepiece \
    protobuf \
    peft \
    g2p-en \
    soundfile

# Download NLTK data required by g2p-en (used by FastSpeech2ConformerTokenizer).
RUN python3 -c "import nltk; nltk.download('averaged_perceptron_tagger_eng'); nltk.download('cmudict')"

# Copy the full repository
COPY . /app

# Default entrypoint
ENTRYPOINT ["bash"]

# Keep-alive CMD so the Space runtime stays healthy. HF Jobs and `docker run`
# override this with their own command (e.g. `run_cohere.sh`).
EXPOSE 7860
CMD ["-c", "python3 -m http.server 7860"]