FROM node:20-alpine

WORKDIR /app

# ffmpeg: audio conversion for AWS Transcribe (WebM → PCM)
# curl: download Whisper models for browser-based transcription
RUN apk add --no-cache ffmpeg curl

COPY package.json ./
RUN npm install --omit=dev

COPY . .

RUN mkdir -p /app/data/logs

# Download Browser Whisper models (self-hosted, no CDN dependency)
RUN mkdir -p /app/public/models/Xenova/whisper-tiny.en/onnx && \
    cd /app/public/models/Xenova/whisper-tiny.en && \
    echo "Downloading Whisper model files..." && \
    curl -sL -o config.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/config.json && \
    curl -sL -o tokenizer.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/tokenizer.json && \
    curl -sL -o preprocessor_config.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/preprocessor_config.json && \
    curl -sL -o generation_config.json https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/generation_config.json && \
    curl -sL -o onnx/encoder_model_quantized.onnx https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/onnx/encoder_model_quantized.onnx && \
    curl -sL -o onnx/decoder_model_merged_quantized.onnx https://huggingface.co/Xenova/whisper-tiny.en/resolve/main/onnx/decoder_model_merged_quantized.onnx && \
    cd /app/public/models && \
    curl -sL -o transformers.min.js https://cdn.jsdelivr.net/npm/@xenova/transformers@2.17.2/dist/transformers.min.js && \
    echo "Whisper models downloaded successfully"

EXPOSE 3000

HEALTHCHECK --interval=30s --timeout=5s --start-period=20s \
  CMD wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1

CMD ["node", "server.js"]

