Upload README.md with huggingface_hub

README.md

@@ -36,8 +36,10 @@ 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 | 154.415 ms | 35 - 133 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 | 13.793 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 | TFLite | 159.429 ms | 24 - 125 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 | 23.342 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 | 622.656 ms | 0 - 83 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 | 23.335 ms | 39 - 55 MB | FP16 | NPU |  [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/WhisperDecoder.so) 
 
 
 ## Installation
@@ -98,17 +100,17 @@ python -m qai_hub_models.models.whisper_base_en.export
 ```
 Profile Job summary of WhisperEncoder
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 157.80 ms
-Estimated Peak Memory Range: 24.20-118.90 MB
-Compute Units: GPU (303) | Total (303)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 459.78 ms
+Estimated Peak Memory Range: 0.92-0.92 MB
+Compute Units: NPU (579) | Total (579)
 
 Profile Job summary of WhisperDecoder
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 13.93 ms
-Estimated Peak Memory Range: 5.49-8.05 MB
-Compute Units: NPU (447),CPU (2) | Total (449)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 13.48 ms
+Estimated Peak Memory Range: 40.50-40.50 MB
+Compute Units: NPU (821) | Total (821)
 
 
 ```