Update README.md

README.md

@@ -9,7 +9,7 @@ Yolov5 is a one-stage structure target detection network framework, in which the
 
 The YOLOv5 model can be found [here](https://github.com/ultralytics/yolov5)
 
-|Device|SoC|Runtime|Model|Size (pixels)|Inference Time (ms)|Precision|Compute Unity|Model Download|
+|Device|SoC|Runtime|Model|Size (pixels)|Inference Time (ms)|Precision|Compute Unit|Model Download|
 |:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|:----:|
 |AidBox QCS6490|QCS6490|QNN|YOLOv5s(cutoff)|640|6.7|INT8|NPU|[model download](https://huggingface.co/aidlux/YOLOv5/blob/main/QCS6490/cutoff_yolov5s_int8.qnn.serialized.bin)|
 |AidBox QCS6490|QCS6490|QNN|YOLOv5s(cutoff)|640|15.2|INT16|NPU|[model download](https://huggingface.co/aidlux/YOLOv5/blob/main/QCS6490/cutoff_yolov5s_int16.qnn.serialized.bin)|