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 | 0.536 ms | 0 - 1 MB | FP16 | NPU |  [MediaPipeFaceDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.209 ms | 0 - 2 MB | FP16 | NPU |  [MediaPipeFaceLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.592 ms | 1 - 55 MB | FP16 | NPU |  [MediaPipeFaceDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.so) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.286 ms | 0 - 8 MB | FP16 | NPU |  [MediaPipeFaceLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.532 ms | 0 - 2 MB | FP16 | NPU |  [MediaPipeFaceDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.211 ms | 0 - 2 MB | FP16 | NPU |  [MediaPipeFaceLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.535 ms | 0 - 4 MB | FP16 | NPU |  [MediaPipeFaceDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.21 ms | 0 - 2 MB | FP16 | NPU |  [MediaPipeFaceLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.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_face]"
+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_face.export
 ```
 Profile Job summary of MediaPipeFaceDetector
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 0.54 ms
-Estimated Peak Memory Range: 0.01-1.47 MB
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 0.38 ms
+Estimated Peak Memory Range: 0.01-26.15 MB
 Compute Units: NPU (111) | Total (111)
 
 Profile Job summary of MediaPipeFaceLandmarkDetector
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 0.21 ms
-Estimated Peak Memory Range: 0.02-1.72 MB
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 0.16 ms
+Estimated Peak Memory Range: 0.01-23.55 MB
 Compute Units: NPU (100) | Total (100)
 
 Profile Job summary of MediaPipeFaceDetector
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 0.59 ms
-Estimated Peak Memory Range: 0.77-54.90 MB
-Compute Units: NPU (147) | Total (147)
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 0.38 ms
+Estimated Peak Memory Range: 0.01-25.70 MB
+Compute Units: NPU (111) | Total (111)
 
 Profile Job summary of MediaPipeFaceLandmarkDetector
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 0.29 ms
-Estimated Peak Memory Range: 0.44-8.36 MB
-Compute Units: NPU (106) | Total (106)
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 0.16 ms
+Estimated Peak Memory Range: 0.02-23.84 MB
+Compute Units: NPU (100) | Total (100)
 
 
 ```
@@ -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-Face-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
 * [BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs](https://arxiv.org/abs/1907.05047)