Dockerfile

# Use a lightweight Python base
FROM python:3.10-slim

# Prevent interactive prompts & speed up Python
ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1 \
    TOKENIZERS_PARALLELISM=false

# Set work directory
WORKDIR /code

# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    git \
    curl \
    wget \
    libopenblas-dev \
    libomp-dev \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first (for Docker caching)
COPY requirements.txt .

# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt

# Hugging Face tools
RUN pip install --no-cache-dir huggingface-hub accelerate

# Install additional dependencies
RUN pip install --no-cache-dir outetts uroman

# Clone yarngpt repository
RUN git clone https://github.com/saheedniyi02/yarngpt.git /tmp/yarngpt && \
    pip install --no-cache-dir /tmp/yarngpt && \
    rm -rf /tmp/yarngpt

# Set Hugging Face cache inside container (persistent, not /tmp)
ENV HF_HOME=/models/huggingface
ENV TRANSFORMERS_CACHE=/models/huggingface
ENV HUGGINGFACE_HUB_CACHE=/models/huggingface
ENV HF_HUB_CACHE=/models/huggingface

# Create cache dir and models directory
RUN mkdir -p /models/huggingface && \
    mkdir -p /code/models

# Pre-download model at build time (YarnGPT2 model)
RUN python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='saheedniyi/YarnGPT2')"

# Preload tokenizer (avoid runtime delays)
RUN python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('saheedniyi/YarnGPT2', use_fast=True)"

# Download wavtokenizer configuration file
RUN wget -O /code/models/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml \
    https://huggingface.co/novateur/WavTokenizer-medium-speech-75token/resolve/main/wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml

# Note: Checkpoint file must be downloaded separately or mounted as volume
# The checkpoint is large and may not download during build
RUN echo "Note: wavtokenizer_large_speech_320_24k.ckpt must be provided separately"

# Copy project files
COPY . .

# Expose FastAPI port
EXPOSE 8000

# Run FastAPI app with uvicorn (2 workers for better concurrency)
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "2"]