Use local Whisper compose stack

docker-compose.yml

@@ -1,3 +1,5 @@
+version: '3.9'
+
 services:
   flynn:
     build: .
@@ -29,28 +31,39 @@ services:
       timeout: 5s
       start_period: 15s
       retries: 3
+    depends_on:
+      whisper-server:
+        condition: service_healthy
+    networks:
+      - flynn-net
 
   # Optional: Whisper server for audio transcription
-  # Uncomment and adjust as needed for voice message support
-  # whisper-server:
-  #   image: ghcr.io/ggml-org/whisper.cpp:main
-  #   container_name: whisper-server
-  #   restart: unless-stopped
-  #   ports:
-  #     - "18801:8080"
-  #   command: whisper-server
-  #     --model /app/models/ggml-base.en.bin
-  #     --host 0.0.0.0
-  #     --port 8080
-  #     --convert
-  #     --language en
-  #     --inference-path /v1/audio/transcriptions
-  #   healthcheck:
-  #     test: ["CMD-SHELL", "curl", "-f", "http://localhost:8080/"]
-  #     interval: 30s
-  #     timeout: 5s
-  #     start_period: 15s
-  #     retries: 3
+  whisper-server:
+    image: ghcr.io/ggml-org/whisper.cpp:main
+    container_name: whisper-server
+    restart: unless-stopped
+    ports:
+      - "18801:8080"
+    command: >
+      whisper-server
+      --model /app/models/ggml-base.en.bin
+      --host 0.0.0.0
+      --port 8080
+      --convert
+      --language en
+      --inference-path /v1/audio/transcriptions
+    volumes:
+      - ./whisper-models:/app/models:ro
+    healthcheck:
+      test: ["CMD-SHELL", "curl", "-f", "http://localhost:8080/"]
+      interval: 30s
+      timeout: 5s
+      start_period: 15s
+      retries: 3
+    networks:
+      - flynn-net
 
 volumes:
   flynn-data:
+networks:
+  flynn-net: