Add local Whisper speech recognition

compose.yaml

@@ -545,7 +545,9 @@ services:
       TTS_MODEL: piper
       TTS_VOICES: alloy
       TTS_DEFAULT_VOICE: alloy
-      ENABLE_STT: "false"
+      ENABLE_STT: "true"
+      STT_WORKER_URL: http://whisper:8084
+      STT_TIMEOUT: "300"
     networks: [frontend, control, inference]
     security_opt: ["no-new-privileges:true"]
     cap_drop: [ALL]
@@ -569,6 +571,8 @@ services:
         condition: service_healthy
       tts-gateway:
         condition: service_healthy
+      whisper:
+        condition: service_healthy
 
   image-worker:
     build:
@@ -710,6 +714,39 @@ services:
       retries: 12
       start_period: 10s
 
+  whisper:
+    build:
+      context: .
+      dockerfile: platform/docker/whisper/Dockerfile
+      args:
+        WHISPER_CPP_VERSION: ${WHISPER_CPP_VERSION:-v1.9.1}
+    image: mike-ai/whisper:local
+    container_name: mike-ai-whisper
+    restart: unless-stopped
+    read_only: true
+    tmpfs:
+      - /tmp:size=2g,mode=1777
+    volumes:
+      - whisper-data:/models
+    environment:
+      WHISPER_HOST: 0.0.0.0
+      WHISPER_PORT: "8084"
+      WHISPER_CLI: /opt/whisper.cpp/build/bin/whisper-cli
+      WHISPER_MODEL: /models/ggml-large-v3-turbo.bin
+      WHISPER_MODEL_URL: ${WHISPER_MODEL_URL:-https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-turbo.bin}
+      WHISPER_THREADS: ${WHISPER_THREADS:-8}
+      WHISPER_LANGUAGE: ${WHISPER_LANGUAGE:-de}
+    networks: [frontend, inference]
+    security_opt: ["no-new-privileges:true"]
+    cap_drop: [ALL]
+    cap_add: [CHOWN, SETUID, SETGID]
+    healthcheck:
+      test: [CMD, curl, -fsS, "http://127.0.0.1:8084/status"]
+      interval: 10s
+      timeout: 5s
+      retries: 90
+      start_period: 20m
+
   llama-dashboard:
     build: ./platform/llama-dashboard
     image: mike-ai/llama-dashboard:local
@@ -809,6 +846,7 @@ networks:
 
 volumes:
   piper-data:
+  whisper-data:
   router-state:
   router-images:
   portainer-data: