Livrare LOT 1 - Didi

ai_platform/modules/audio/deploy/docker-compose.yml

@@ -0,0 +1,95 @@
+# Audio Module - Docker Compose Configuration
+#
+# Port Allocation (Dev AI Audio: 54300):
+#   54300 - Audio API (Whisper STT service)
+#
+# Profiles:
+#   api       - API server only
+#
+# Required environment variables (set in deploy/.env file):
+#   AUDIO_MODEL                - Whisper model name (e.g., large-v3-turbo)
+#   AUDIO_DEVICE               - Device: cuda or cpu
+#   AUDIO_COMPUTE_TYPE         - Compute type: int8, float16, int8_float16
+#   AUDIO_CACHE_DIR            - Model cache directory
+#
+# GPU Configuration:
+#   - Runs on GPU 0 (shared with Qwen3.5-35B-A3B)
+#   - Requires ~6GB VRAM for large-v3-turbo with int8
+#
+# Naming Convention: didiAI-{module}-{service}
+#
+# Network:
+#   Uses deploy_default network (shared with other modules)
+
+networks:
+  deploy_default:
+    external: true
+
+services:
+  # ==========================================================================
+  # Audio Transcription API Server
+  # ==========================================================================
+  audio-api:
+    container_name: didiAI-audio-api
+    image: didiai-audio-api
+    build:
+      context: ..
+      dockerfile: deploy/Dockerfile
+
+    ports:
+      - "54300:54300"
+    networks:
+      - deploy_default
+
+    environment:
+      # GPU configuration
+      - CUDA_VISIBLE_DEVICES=0
+
+      # External URL for OpenAPI spec (REQUIRED)
+      - AUDIO_EXTERNAL_URL=${AUDIO_EXTERNAL_URL}
+
+      # Whisper model configuration
+      - AUDIO_MODEL=${AUDIO_MODEL:-large-v3-turbo}
+      - AUDIO_DEVICE=${AUDIO_DEVICE:-cuda}
+      - AUDIO_COMPUTE_TYPE=${AUDIO_COMPUTE_TYPE:-int8}
+      - AUDIO_CACHE_DIR=${AUDIO_CACHE_DIR:-/root/.cache/huggingface}
+
+      # Transcription settings
+      - AUDIO_BEAM_SIZE=${AUDIO_BEAM_SIZE:-5}
+      - AUDIO_BEST_OF=${AUDIO_BEST_OF:-5}
+      - AUDIO_TEMPERATURE=${AUDIO_TEMPERATURE:-0.0}
+
+      # Server settings
+      - AUDIO_HOST=0.0.0.0
+      - AUDIO_PORT=54300
+      - AUDIO_LOG_LEVEL=${AUDIO_LOG_LEVEL:-INFO}
+
+      # Runtime config polling
+      - AUDIO_DASHBOARD_URL=${AUDIO_DASHBOARD_URL:-http://didiAI-dashboard:51300}
+
+      # Upload limits
+      - AUDIO_MAX_FILE_SIZE_MB=${AUDIO_MAX_FILE_SIZE_MB:-500}
+
+    volumes:
+      # Model cache (shared with other modules)
+      - ${AUDIO_CACHE_DIR:-/root/.cache/huggingface}:/root/.cache/huggingface
+
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: ['0']
+              capabilities: [gpu]
+
+    healthcheck:
+      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:54300/health')"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+
+    restart: unless-stopped
+    profiles:
+      - api
+