Kleineres Modell

scripts/clone_model.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+case "${1:-}" in
+  load|start)
+    docker compose --profile clone up -d qwen3-tts-clone
+    ;;
+  unload|stop)
+    docker compose --profile clone stop qwen3-tts-clone >/dev/null
+    docker compose --profile clone rm -f qwen3-tts-clone >/dev/null
+    ;;
+  status)
+    docker ps --filter "name=qwen3-tts-clone" --format '{{.Names}} {{.Status}} {{.Ports}}'
+    ;;
+  logs)
+    docker logs -f qwen3-tts-clone
+    ;;
+  *)
+    echo "Usage: $0 {load|unload|status|logs}" >&2
+    echo "Set QWEN3_TTS_CLONE_MODEL=<model-id> before load if needed." >&2
+    exit 2
+    ;;
+esac

scripts/download_qwen3_tts_base.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+set -euo pipefail
+cd "$(dirname "$0")"
+MODEL="${QWEN3_TTS_BASE_MODEL:-Qwen/Qwen3-TTS-12Hz-1.7B-Base}"
+CACHE_ROOT="/home/guru/vllm/data/root"
+mkdir -p "$CACHE_ROOT/.cache/huggingface"
+
+printf "Lade %s in gemeinsamen Container-Cache...\n" "$MODEL"
+docker run --rm \
+  -e HF_HOME=/root/.cache/huggingface \
+  -v "$CACHE_ROOT:/root" \
+  vllm/vllm-omni:latest-aarch64 \
+  python3 -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='$MODEL')"
+
+printf "Fertig. Danach: ./start_dialog_tts.sh\n"

scripts/start.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+set -e
+cd "$(dirname "$0")"
+exec ./start_tts.sh "$@"

scripts/start_clone.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+HEALTH_URL="http://localhost:8091/health"
+MAX_WAIT="${MAX_WAIT:-180}"
+[ -f .env ] && source .env
+MODEL="${QWEN3_TTS_CLONE_MODEL:-Qwen/Qwen3-TTS-12Hz-1.7B-Base}"
+
+t0=$SECONDS
+printf "TTS-Container stoppt..."
+docker compose stop qwen3-tts >/dev/null 2>&1 || true
+docker compose rm -f qwen3-tts >/dev/null 2>&1 || true
+printf " [%ds]
+" $(( SECONDS - t0 ))
+
+printf "Clone-Container startet..."
+docker compose --profile clone up -d qwen3-tts-clone >/tmp/qwen3-tts-clone-compose.log 2>&1
+printf " [%ds]
+" $(( SECONDS - t0 ))
+printf "  Modell   %s
+" "$MODEL"
+printf "  API      http://localhost:8091
+
+"
+
+while (( SECONDS - t0 < MAX_WAIT )); do
+    if curl -sf "$HEALTH_URL" >/dev/null 2>&1; then
+        printf "✓  Clone bereit: http://localhost:8091  [%ds]
+" $(( SECONDS - t0 ))
+        exit 0
+    fi
+
+    if ! docker ps --filter "name=qwen3-tts-clone" --filter "status=running" -q | grep -q .; then
+        printf "✗  Clone-Container abgestürzt. Logs:
+" >&2
+        docker logs --tail=40 qwen3-tts-clone 2>&1 >&2 || true
+        exit 1
+    fi
+    sleep 2
+done
+
+printf "✗  Timeout nach %ss. Logs: docker logs qwen3-tts-clone
+" "$MAX_WAIT" >&2
+exit 1

scripts/start_custom_tts.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+set -euo pipefail
+cd "$(dirname "$0")"
+export QWEN3_TTS_MODEL="${QWEN3_TTS_MODEL:-Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice}"
+exec ./start_tts.sh

scripts/start_dialog_tts.sh

@@ -0,0 +1,5 @@
+#!/bin/bash
+set -euo pipefail
+cd "$(dirname "$0")"
+export QWEN3_TTS_MODEL="${QWEN3_TTS_MODEL:-Qwen/Qwen3-TTS-12Hz-1.7B-Base}"
+exec ./start_tts.sh

scripts/start_tts.sh

@@ -0,0 +1,80 @@
+#!/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

scripts/stop_clone.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+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 "✓  Clone-Service gestoppt
+"

scripts/stop_tts.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+set -euo pipefail
+cd "$(dirname "$0")/.."
+
+docker compose stop qwen3-tts >/dev/null 2>&1 || true
+docker compose rm -f qwen3-tts >/dev/null 2>&1 || true
+printf "✓  TTS/UI gestoppt
+"