fegger
ef59fc0fb4
- server/whisper-server: compose stack built from the pinned whisper.cpp v1.9.3 release, same as the Android JNI layer - Vulkan GPU backend (AMD Radeon AI PRO R9700 / RADV) with transparent CPU fallback and NO_GPU override; GGML models auto-download on first start (MODEL env, default large-v3) - API bound to the Tailscale interface only (100.103.83.12:8080) since whisper-server has no authentication; render-group GID passthrough for /dev/dri - validated locally: image builds, entrypoint downloads tiny, POST /inference returns verbose_json with language + segments; GPU-less fallback confirmed
35 lines
921 B
Bash
35 lines
921 B
Bash
#!/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" |