# Lightweight Python image
FROM python:3.10-slim

# System deps
RUN apt-get update && apt-get install -y --no-install-recommends \
    ffmpeg git build-essential \
 && rm -rf /var/lib/apt/lists/*

# Make writable dirs for caches and NLTK
RUN mkdir -p /data/nltk_data \
    /data/huggingface/transformers \
    /data/huggingface/datasets \
    /data/tmp && chmod -R 777 /data

# Point all caches to /data (writable)
ENV NLTK_DATA=/data/nltk_data
ENV HF_HOME=/data/huggingface
ENV TRANSFORMERS_CACHE=/data/huggingface/transformers
ENV HF_DATASETS_CACHE=/data/huggingface/datasets
ENV TMPDIR=/data/tmp

# Optional: choose Whisper size via env (ignored now if using SpeechRecognition)
ENV WHISPER_MODEL=base

WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY app.py .
COPY README.md . 

# Spaces expects port 7860
ENV PORT=7860

# Start FastAPI
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]