Implemented experimental real production ready voice chat, relegated old flow to voice debug mode. New Web UI panel for Voice Chat.

docker-compose.yml

@@ -78,7 +78,7 @@ services:
 
   miku-stt:
     build:
-      context: ./stt-parakeet
+      context: ./stt-realtime
       dockerfile: Dockerfile
     container_name: miku-stt
     runtime: nvidia
@@ -86,10 +86,14 @@ services:
       - NVIDIA_VISIBLE_DEVICES=0  # GTX 1660
       - CUDA_VISIBLE_DEVICES=0
       - NVIDIA_DRIVER_CAPABILITIES=compute,utility
+      - STT_HOST=0.0.0.0
+      - STT_PORT=8766
+      - STT_HTTP_PORT=8767  # HTTP health check port
     volumes:
-      - ./stt-parakeet/models:/app/models  # Persistent model storage
+      - stt-models:/root/.cache/huggingface  # Persistent model storage
     ports:
       - "8766:8766"  # WebSocket port
+      - "8767:8767"  # HTTP health check port
     networks:
       - miku-voice
     deploy:
@@ -100,7 +104,6 @@ services:
               device_ids: ['0']  # GTX 1660
               capabilities: [gpu]
     restart: unless-stopped
-    command: ["python3.11", "-m", "server.ws_server", "--host", "0.0.0.0", "--port", "8766", "--model", "nemo-parakeet-tdt-0.6b-v3"]
 
   anime-face-detector:
     build: ./face-detector
@@ -128,3 +131,7 @@ networks:
   miku-voice:
     external: true
     name: miku-voice-network
+
+volumes:
+  stt-models:
+    name: miku-stt-models