Upload README.md with huggingface_hub

README.md

@@ -38,10 +38,10 @@ 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 | 159.078 ms | 0 - 97 MB | FP16 | GPU |  [WhisperEncoder.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/WhisperEncoder.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 23.491 ms | 6 - 8 MB | FP16 | NPU |  [WhisperDecoder.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/WhisperDecoder.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 467.575 ms | 0 - 84 MB | FP16 | NPU |  [WhisperEncoder.so](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/WhisperEncoder.so) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 23.659 ms | 40 - 55 MB | FP16 | NPU |  [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/WhisperDecoder.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 158.707 ms | 24 - 124 MB | FP16 | GPU |  [WhisperEncoder.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/WhisperEncoder.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 23.494 ms | 6 - 8 MB | FP16 | NPU |  [WhisperDecoder.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/WhisperDecoder.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 450.599 ms | 0 - 79 MB | FP16 | NPU |  [WhisperEncoder.so](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/WhisperEncoder.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 3.979 ms | 9 - 200 MB | FP16 | NPU |  [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/WhisperDecoder.so) 
 
 
 
@@ -104,15 +104,15 @@ python -m qai_hub_models.models.whisper_base_en.export
 Profile Job summary of WhisperEncoder
 --------------------------------------------------
 Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 467.55 ms
-Estimated Peak Memory Range: 0.05-84.05 MB
-Compute Units: NPU (580) | Total (580)
+Estimated Inference Time: 448.13 ms
+Estimated Peak Memory Range: 0.05-95.81 MB
+Compute Units: NPU (531) | Total (531)
 
 Profile Job summary of WhisperDecoder
 --------------------------------------------------
 Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 23.55 ms
-Estimated Peak Memory Range: 40.47-56.10 MB
+Estimated Inference Time: 4.01 ms
+Estimated Peak Memory Range: 5.11-206.12 MB
 Compute Units: NPU (821) | Total (821)