Dockerfile

FROM nvidia/cuda:12.8.0-runtime-ubuntu22.04

# Avoid interactive prompts
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1

# System deps
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.11 python3.11-venv python3-pip git ffmpeg libsndfile1 \
    && rm -rf /var/lib/apt/lists/*

RUN ln -sf /usr/bin/python3.11 /usr/bin/python3 && \
    ln -sf /usr/bin/python3.11 /usr/bin/python

WORKDIR /app

# 1. Install PyTorch for CUDA 12.8 (Blackwell / Ada / Ampere)
RUN pip install --no-cache-dir \
    torch torchaudio --index-url https://download.pytorch.org/whl/cu128

# 2. Install chatterbox WITHOUT its pinned torch (--no-deps), then install remaining deps
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# 3. Copy app + LoRA weights
COPY app.py .
COPY checkpoints/ checkpoints/
COPY tokenizer/ tokenizer/
COPY conds/ conds/

# Pre-download base Chatterbox weights at build time (optional, ~2GB)
# Uncomment to bake weights into image (larger image, faster cold start):
# RUN python3 -c "from chatterbox.mtl_tts import ChatterboxMultilingualTTS; ChatterboxMultilingualTTS.from_pretrained('cpu')"

EXPOSE 7860

CMD ["python3", "app.py", "--device", "auto"]