Qwen3-tts/scripts/start_tts.sh

#!/bin/bash
set -e
cd "$(dirname "$0")/.."

HEALTH_URL="http://localhost:8091/health"
MAX_WAIT=180
# .env aus dem Projektroot laden (nur falls Variable nicht schon im Shell-Env gesetzt)
[ -f .env ] && source .env
MODEL="${QWEN3_TTS_MODEL:-Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice}"

strip_ansi() { sed 's/\x1b\[[0-9;]*[mK]//g'; }

t0=$SECONDS

# --- Gegenseitigen Service stoppen ---
printf "Clone-Container stoppt..."
docker compose --profile clone stop qwen3-tts-clone >/dev/null 2>&1 || true
docker compose --profile clone rm -f qwen3-tts-clone >/dev/null 2>&1 || true
printf " [%ds]
" $(( SECONDS - t0 ))

# --- Container starten ---
printf "TTS-Container startet..."
docker compose up -d qwen3-tts &>/tmp/qwen3-tts-compose.log
printf " [%ds]\n" $(( SECONDS - t0 ))
printf "  Modell   %s\n\n" "$MODEL"

# --- Log-Events im Hintergrund parsen und ausgeben ---
docker logs -f qwen3-tts 2>&1 | strip_ansi | while IFS= read -r line; do
    case "$line" in
        *"Stage 0 engine launch started"*)
            printf "  Stage 0  Talker LLM wird geladen\n" ;;
        *"Initializing a V1 LLM engine"*)
            printf "  Stage 0  Engine initialisiert\n" ;;
        *"Loading weights"*)
            printf "  Stage 0  Modell-Gewichte werden geladen...\n" ;;
        *"Loading model weights took"*)
            took=$(echo "$line" | grep -oP '\d+\.\d+s' | head -1)
            printf "  Stage 0  Gewichte geladen (%s)\n" "$took" ;;
        *"Stage 1 engine launch started"*)
            printf "  Stage 1  Code2Wav Decoder wird geladen\n" ;;
        *"Graph capturing finished"*)
            printf "  CUDA     Graphen kompiliert\n" ;;
        *"Application startup complete"*)
            printf "  Server   FastAPI bereit\n" ;;
        *"Uvicorn running on"*)
            printf "  Server   HTTP läuft auf Port 8091\n" ;;
        *"warmup] Server gesund"*)
            printf "  Warmup   Aufwärm-Request läuft (kompiliert/lädt Graphen)...\n" ;;
        *"warmup] fertig"*)
            took=$(echo "$line" | grep -oP '\d+s' | head -1)
            printf "  Warmup   Server ist heiß (%s)\n" "$took" ;;
        *"ERROR"*|*"ValueError"*)
            msg=$(echo "$line" | grep -oP '(ERROR|ValueError).*' | head -1)
            printf "  [!] %s\n" "${msg:0:100}" ;;
    esac
done &
LOG_PID=$!

# --- Health-Check-Schleife ---
while (( SECONDS - t0 < MAX_WAIT )); do
    if curl -sf "$HEALTH_URL" >/dev/null 2>&1; then
        kill "$LOG_PID" 2>/dev/null
        wait "$LOG_PID" 2>/dev/null || true
        printf "\n✓  Bereit: API http://localhost:8091  UI http://localhost:8092  WS-Log ws://localhost:8094/v1/audio/speech/stream  [%ds]\n" $(( SECONDS - t0 ))
        exit 0
    fi
    # Abbruch wenn Container schon gestoppt ist
    if ! docker ps --filter "name=qwen3-tts" --filter "status=running" -q | grep -q .; then
        kill "$LOG_PID" 2>/dev/null
        printf "\n✗  Container abgestürzt. Logs:\n"
        docker logs --tail=20 qwen3-tts 2>&1 | strip_ansi | grep -E "ERROR|ValueError|Exception" | head -5
        exit 1
    fi
    sleep 2
done

kill "$LOG_PID" 2>/dev/null
printf "\n✗  Timeout nach %ds. Logs: docker logs qwen3-tts\n" "$MAX_WAIT" >&2
exit 1