Upload README.md with huggingface_hub

README.md

@@ -34,8 +34,8 @@ 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 | 244.369 ms | 7 - 10 MB | FP16 | NPU |  [TrOCREncoder.tflite](https://huggingface.co/qualcomm/TrOCR/blob/main/TrOCREncoder.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 2.82 ms | 0 - 2 MB | FP16 | NPU |  [TrOCRDecoder.tflite](https://huggingface.co/qualcomm/TrOCR/blob/main/TrOCRDecoder.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 243.976 ms | 7 - 10 MB | FP16 | NPU |  [TrOCREncoder.tflite](https://huggingface.co/qualcomm/TrOCR/blob/main/TrOCREncoder.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 2.81 ms | 0 - 2 MB | FP16 | NPU |  [TrOCRDecoder.tflite](https://huggingface.co/qualcomm/TrOCR/blob/main/TrOCRDecoder.tflite) 
 
 
 ## Installation
@@ -96,16 +96,16 @@ python -m qai_hub_models.models.trocr.export
 ```
 Profile Job summary of TrOCREncoder
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 244.37 ms
-Estimated Peak Memory Range: 6.96-9.97 MB
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 182.19 ms
+Estimated Peak Memory Range: 0.02-291.46 MB
 Compute Units: NPU (627) | Total (627)
 
 Profile Job summary of TrOCRDecoder
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 2.82 ms
-Estimated Peak Memory Range: 0.02-2.11 MB
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 2.02 ms
+Estimated Peak Memory Range: 0.01-184.44 MB
 Compute Units: NPU (394) | Total (394)
 
 
@@ -211,7 +211,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 ## License
 - The license for the original implementation of TrOCR can be found
   [here](https://github.com/microsoft/unilm/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
 * [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://arxiv.org/abs/2109.10282)