update README.md

README.md

@@ -44,6 +44,7 @@ docker run -it \
 ```bash
 pip uninstall vllm
 pip install vllm-0.15.1+das.opt1.alpha.dtk2604-cp310-cp310-linux_x86_64.whl
+pip install numpy==1.25.0
 pip install -r requirements.txt
 ```
 
@@ -67,14 +68,14 @@ python inference.py
 ## serve启动
 export VLLM_USE_FUSED_RMS_ROPE=0
 
-vllm serve /path/Qwen3-ASR/Qwen3-ASR-1.7B \
+vllm serve Qwen/Qwen3-ASR-1.7B \
     --trust-remote-code \
     --limit-mm-per-prompt '{"audio": 1}'
 
 ## client访问
 curl -X POST "http://127.0.0.1:8000/v1/audio/transcriptions" \
     -F "file=@/path/to/test.wav" \
-    -F "model=/path/Qwen3-ASR/Qwen3-ASR-1.7B"
+    -F "model=Qwen/Qwen3-ASR-1.7B"
 ```
 
 ## 效果展示

requirements.txt

@@ -10,3 +10,4 @@ gradio
 flask
 pytz
 pycountry
+qwen-asr
\ No newline at end of file