Upload README.md with huggingface_hub

README.md

@@ -35,8 +35,8 @@ More details on model performance across various devices, can be found
 
 | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
 | ---|---|---|---|---|---|---|---|
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.086 ms | 0 - 2 MB | INT8 | NPU |  [XLSR-Quantized.tflite](https://huggingface.co/qualcomm/XLSR-Quantized/blob/main/XLSR-Quantized.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.801 ms | 0 - 14 MB | INT8 | NPU |  [XLSR-Quantized.so](https://huggingface.co/qualcomm/XLSR-Quantized/blob/main/XLSR-Quantized.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.125 ms | 0 - 1 MB | INT8 | NPU |  [XLSR-Quantized.tflite](https://huggingface.co/qualcomm/XLSR-Quantized/blob/main/XLSR-Quantized.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.651 ms | 0 - 3 MB | INT8 | NPU |  [XLSR-Quantized.so](https://huggingface.co/qualcomm/XLSR-Quantized/blob/main/XLSR-Quantized.so) 
 
 
 
@@ -98,10 +98,10 @@ python -m qai_hub_models.models.xlsr_quantized.export
 ```
 Profile Job summary of XLSR-Quantized
 --------------------------------------------------
-Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 0.80 ms
-Estimated Peak Memory Range: 0.06-33.15 MB
-Compute Units: NPU (17) | Total (17)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 0.71 ms
+Estimated Peak Memory Range: 0.06-0.06 MB
+Compute Units: NPU (16) | Total (16)
 
 
 ```
@@ -109,6 +109,20 @@ Compute Units: NPU (17) | Total (17)
 
 
 
+## Run demo on a cloud-hosted device
+
+You can also run the demo on-device.
+
+```bash
+python -m qai_hub_models.models.xlsr_quantized.demo --on-device
+```
+
+**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
+environment, please add the following to your cell (instead of the above).
+```
+%run -m qai_hub_models.models.xlsr_quantized.demo -- --on-device
+```
+
 
 ## Deploying compiled model to Android