initial

docker-compose.yml

@@ -0,0 +1,46 @@
+services:
+  whisper-models-init:
+    build:
+      context: .
+    image: ${OPENAI_WHISPER_IMAGE:-rk-whisper-stt-api:latest}
+    command: ["python", "/app/app/download_models.py", "--target", "/models"]
+    volumes:
+      - whisper-models:/models
+    profiles: ["init"]
+
+  whisper-stt:
+    build:
+      context: .
+    image: ${OPENAI_WHISPER_IMAGE:-rk-whisper-stt-api:latest}
+    restart: unless-stopped
+    ports:
+      - "${STT_PORT:-9000}:9000"
+    environment:
+      MODEL_NAME: ${MODEL_NAME:-whisper-base-onnx}
+      STT_API_KEY: ${STT_API_KEY:-}
+      ENCODER_MODEL_PATH: /models/whisper_encoder_base_20s.onnx
+      DECODER_MODEL_PATH: /models/whisper_decoder_base_20s.onnx
+      MEL_FILTERS_PATH: /models/mel_80_filters.txt
+      VOCAB_EN_PATH: /models/vocab_en.txt
+      VOCAB_ZH_PATH: /models/vocab_zh.txt
+      MAX_DECODE_TOKENS: ${MAX_DECODE_TOKENS:-128}
+      VLM_ENABLED: ${VLM_ENABLED:-false}
+      VLM_MODEL_NAME: ${VLM_MODEL_NAME:-qwen3-vl-2b-rkllm}
+      VLM_CORE_NUM: ${VLM_CORE_NUM:-3}
+      VLM_MAX_NEW_TOKENS: ${VLM_MAX_NEW_TOKENS:-256}
+      VLM_MAX_CONTEXT_LEN: ${VLM_MAX_CONTEXT_LEN:-4096}
+      VLM_TIMEOUT_SEC: ${VLM_TIMEOUT_SEC:-300}
+    volumes:
+      - whisper-models:/models:ro
+      - rkllm-root:/opt/rkllm-root:ro
+    devices:
+      - /dev/dri:/dev/dri
+    healthcheck:
+      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:9000/health')"]
+      interval: 20s
+      timeout: 5s
+      retries: 3
+
+volumes:
+  whisper-models:
+  rkllm-root: