#!/bin/sh
# Downloads the configured GGML model on first start, then runs whisper-server.
# Uses the GPU (Vulkan) automatically when one is present; set NO_GPU=1
# to force CPU.
set -eu

MODEL="${MODEL:-small}"
THREADS="${THREADS:-4}"
HOST="${HOST:-0.0.0.0}"
PORT="${PORT:-8080}"
MODEL_DIR="${MODEL_DIR:-/models}"
FILE="$MODEL_DIR/ggml-$MODEL.bin"

mkdir -p "$MODEL_DIR"
if [ ! -s "$FILE" ]; then
    echo "downloading ggml-$MODEL.bin to $FILE ..."
    curl -fL --retry 3 -C - -o "$FILE.part" \
        "https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-$MODEL.bin"
    mv "$FILE.part" "$FILE"
    echo "done."
fi

GPU_FLAGS=""
if [ "${NO_GPU:-0}" = "1" ]; then
    GPU_FLAGS="-ng"
fi

echo "starting whisper-server: model=$MODEL threads=$THREADS host=$HOST port=$PORT gpu=auto"
exec whisper-server \
    -m "$FILE" \
    -l auto \
    -t "$THREADS" \
    $GPU_FLAGS \
    --host "$HOST" \
    --port "$PORT"