fix: uv dependency

Dockerfile

@@ -7,6 +7,7 @@ COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /bin/
 WORKDIR /app
 COPY . .
 RUN uv sync
+RUN uv sync --extra vllm
 
 ENV ASR_MODEL_PATH="Qwen/Qwen3-ASR-1.7B"
 

README_BW.md

@@ -19,14 +19,14 @@ https://github.com/QwenLM/Qwen3-ASR
 # Start
 
 ```bash
-docker pull harbor.bwgdi.com/library/qwen3asr:0.0.1
+docker pull harbor.bwgdi.com/library/qwen3-asr:0.0.1
 
 # Run with custom model path
 # -e ASR_MODEL_PATH: Model name or local path inside container
-docker run -d --restart always -p 8000:8000 --gpus all \
+docker run -d --restart always -p 5051:5000 --gpus all \
   -e ASR_MODEL_PATH="Qwen/Qwen3-ASR-1.7B" \
   --mount type=bind,source=/path/to/your/models,target=/models \
-  harbor.bwgdi.com/library/qwen3asr:0.0.3
+  harbor.bwgdi.com/library/qwen3-asr:0.0.1
 ```
 
 # Usage

examples/api_unified_fastapi.py

@@ -173,7 +173,7 @@ def parse_args():
     p = argparse.ArgumentParser(description="Qwen3-ASR Unified API (streaming + non-streaming)")
     p.add_argument("--asr-model-path", default="Qwen/Qwen3-ASR-1.7B", help="Model name or local path")
     p.add_argument("--host", default="0.0.0.0")
-    p.add_argument("--port", type=int, default=8000)
+    p.add_argument("--port", type=int, default=5000)
     p.add_argument("--gpu-memory-utilization", type=float, default=0.8)
     p.add_argument("--max-new-tokens", type=int, default=32,
                    help="Max new tokens per call (streaming). Use larger value for non-streaming.")