Use Qwen3-ASR as production speech recognizer

compose.yaml

@@ -658,7 +658,7 @@ services:
       MUSIC_START_TIMEOUT: "600"
       VOICE_CHANGE_START_TIMEOUT: "600"
       APPLIO_START_TIMEOUT: "900"
-      STT_WORKER_URL: http://whisper:8084
+      STT_WORKER_URL: http://qwen-asr-worker:8084
       STT_TIMEOUT: "300"
     networks: [frontend, control, inference]
     security_opt: ["no-new-privileges:true"]
@@ -681,7 +681,7 @@ services:
         condition: service_healthy
       tts-gateway:
         condition: service_healthy
-      whisper:
+      qwen-asr-worker:
         condition: service_healthy
 
   image-worker:
@@ -976,40 +976,77 @@ 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
+  qwen-asr:
+    image: ${LLAMA_CPU_IMAGE:-mike-ai/llama.cpp-cpu:local}
+    container_name: mike-ai-qwen-asr
     restart: unless-stopped
     read_only: true
     tmpfs:
-      - /tmp:size=2g,mode=1777
+      - /tmp:size=256m,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-small.bin
-      WHISPER_MODEL_URL: ${WHISPER_MODEL_URL:-https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin}
-      WHISPER_SERVER_PORT: "8085"
-      WHISPER_THREADS: ${WHISPER_THREADS:-8}
-      WHISPER_LANGUAGE: ${WHISPER_LANGUAGE:-de}
-    networks: [frontend, inference]
+      - "${QWEN_ASR_MODEL_DIR:-/data/models/qwen3-asr-0.6b-q8}:/models:ro"
+    command:
+      - --model
+      - /models/Qwen3-ASR-0.6B-Q8_0.gguf
+      - --mmproj
+      - /models/mmproj-Qwen3-ASR-0.6B-Q8_0.gguf
+      - --no-mmproj-offload
+      - --n-gpu-layers
+      - "0"
+      - --alias
+      - qwen3-asr-0.6b
+      - --ctx-size
+      - "4096"
+      - --threads
+      - "6"
+      - --parallel
+      - "1"
+      - --host
+      - 0.0.0.0
+      - --port
+      - "8080"
+      - --no-ui
+      - --fit
+      - "off"
+    cpus: 6
+    mem_limit: 6g
+    networks: [inference]
     security_opt: ["no-new-privileges:true"]
     cap_drop: [ALL]
-    # The entrypoint supervises whisper-server after dropping it to uid 10004.
-    cap_add: [CHOWN, SETUID, SETGID, KILL]
     healthcheck:
-      test: [CMD, curl, -fsS, "http://127.0.0.1:8084/status"]
+      test: [CMD, curl, -fsS, "http://127.0.0.1:8080/health"]
       interval: 10s
       timeout: 5s
-      retries: 90
-      start_period: 20m
+      retries: 12
+      start_period: 30s
+
+  qwen-asr-worker:
+    build:
+      context: .
+      dockerfile: platform/docker/qwen-asr-worker/Dockerfile
+    image: mike-ai/qwen-asr-worker:local
+    container_name: mike-ai-qwen-asr-worker
+    restart: unless-stopped
+    read_only: true
+    tmpfs:
+      - /tmp:size=256m,mode=1777
+    environment:
+      QWEN_ASR_HOST: 0.0.0.0
+      QWEN_ASR_PORT: "8084"
+      QWEN_ASR_LANGUAGE: de
+      QWEN_ASR_SERVER_URL: http://qwen-asr:8080
+    networks: [inference]
+    security_opt: ["no-new-privileges:true"]
+    cap_drop: [ALL]
+    depends_on:
+      qwen-asr:
+        condition: service_healthy
+    healthcheck:
+      test: [CMD, python, -c, "import json,urllib.request; assert json.load(urllib.request.urlopen('http://127.0.0.1:8084/status', timeout=2))['ready']"]
+      interval: 10s
+      timeout: 5s
+      retries: 12
+      start_period: 15s
 
   llama-dashboard:
     build: ./platform/llama-dashboard
@@ -1124,7 +1161,6 @@ networks:
     name: mike-ai-tools-egress
 
 volumes:
-  whisper-data:
   router-state:
   router-images:
   portainer-data: