Dockerfile

FROM python:3.10-slim

# Set up a new user named "user" with user ID 1000 (required by HuggingFace Spaces)
RUN useradd -m -u 1000 user

# Set working directory
WORKDIR /app

# System dependencies for audio processing
RUN apt-get update && apt-get install -y \
    libsndfile1 \
    ffmpeg \
    libgomp1 \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements and install as root
COPY --chown=user requirements.txt /app/requirements.txt
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt

# Install PyTorch CPU wheels for model downloads/runtime
RUN pip install --no-cache-dir torch torchaudio --index-url https://download.pytorch.org/whl/cpu

# Copy application files with correct ownership
COPY --chown=user app.py /app/
COPY --chown=user detector.py /app/
COPY --chown=user self_learning_train.py /app/

# Switch to the "user" user
USER user

# Set home to the user's home directory
ENV HOME=/home/user \
    PATH=/home/user/.local/bin:$PATH \
    PYTHONUNBUFFERED=1

# Pre-download models (will be cached in user's home)
RUN python -c "from transformers import AutoModelForAudioClassification, AutoFeatureExtractor, WhisperProcessor, WhisperForConditionalGeneration; \
    print('Downloading models...'); \
    AutoModelForAudioClassification.from_pretrained('garystafford/wav2vec2-deepfake-voice-detector'); \
    AutoFeatureExtractor.from_pretrained('garystafford/wav2vec2-deepfake-voice-detector'); \
    WhisperProcessor.from_pretrained('openai/whisper-base'); \
    WhisperForConditionalGeneration.from_pretrained('openai/whisper-base'); \
    print('Models downloaded successfully')"

# Expose HuggingFace Spaces port
EXPOSE 7860

# AI_Voice_Detector/Dockerfile (CMD line)
CMD ["gunicorn", "--bind", "0.0.0.0:7860", "app:app"]