Upload README.md with huggingface_hub

README.md

@@ -34,10 +34,10 @@ 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 | 0.762 ms | 0 - 3 MB | FP16 | NPU |  [MediaPipeHandDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.017 ms | 0 - 2 MB | FP16 | NPU |  [MediaPipeHandLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.82 ms | 1 - 6 MB | FP16 | NPU |  [MediaPipeHandDetector.so](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.so) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.088 ms | 1 - 51 MB | FP16 | NPU |  [MediaPipeHandLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.765 ms | 0 - 12 MB | FP16 | NPU |  [MediaPipeHandDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.047 ms | 0 - 2 MB | FP16 | NPU |  [MediaPipeHandLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.763 ms | 0 - 2 MB | FP16 | NPU |  [MediaPipeHandDetector.so](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.996 ms | 0 - 10 MB | FP16 | NPU |  [MediaPipeHandLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.so) 
 
 
 ## Installation
@@ -45,11 +45,10 @@ More details on model performance across various devices, can be found
 This model can be installed as a Python package via pip.
 
 ```bash
-pip install "qai-hub-models[mediapipe_hand]"
+pip install qai-hub-models
 ```
 
 
-
 ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
 
 Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
@@ -98,31 +97,31 @@ python -m qai_hub_models.models.mediapipe_hand.export
 ```
 Profile Job summary of MediaPipeHandDetector
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 0.76 ms
-Estimated Peak Memory Range: 0.01-3.13 MB
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 0.57 ms
+Estimated Peak Memory Range: 0.01-49.27 MB
 Compute Units: NPU (151) | Total (151)
 
 Profile Job summary of MediaPipeHandLandmarkDetector
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 1.02 ms
-Estimated Peak Memory Range: 0.02-2.30 MB
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 0.75 ms
+Estimated Peak Memory Range: 0.02-51.85 MB
 Compute Units: NPU (158) | Total (158)
 
 Profile Job summary of MediaPipeHandDetector
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 0.82 ms
-Estimated Peak Memory Range: 0.77-5.97 MB
-Compute Units: NPU (196) | Total (196)
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 0.55 ms
+Estimated Peak Memory Range: 0.01-49.65 MB
+Compute Units: NPU (151) | Total (151)
 
 Profile Job summary of MediaPipeHandLandmarkDetector
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 1.09 ms
-Estimated Peak Memory Range: 0.55-51.09 MB
-Compute Units: NPU (209) | Total (209)
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 0.75 ms
+Estimated Peak Memory Range: 0.01-51.44 MB
+Compute Units: NPU (158) | Total (158)
 
 
 ```
@@ -227,7 +226,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 ## License
 - The license for the original implementation of MediaPipe-Hand-Detection can be found
   [here](https://github.com/zmurez/MediaPipePyTorch/blob/master/LICENSE).
-- The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf).
+- The license for the compiled assets for on-device deployment can be found [here]({deploy_license_url})
 
 ## References
 * [MediaPipe Hands: On-device Real-time Hand Tracking](https://arxiv.org/abs/2006.10214)