Upload README.md with huggingface_hub

README.md

@@ -34,10 +34,15 @@ More details on model performance across various devices, can be found
   - Model size (WhisperDecoder): 531 MB
 
 
+
+
 | 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 | 617.428 ms | 46 - 474 MB | FP16 | GPU |  [WhisperEncoder.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 26.398 ms | 16 - 20 MB | FP16 | NPU |  [WhisperDecoder.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 610.635 ms | 8 - 417 MB | FP16 | GPU |  [WhisperEncoder.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 26.644 ms | 16 - 20 MB | FP16 | NPU |  [WhisperDecoder.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1969.063 ms | 1 - 216 MB | FP16 | NPU |  [WhisperEncoder.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 24.731 ms | 118 - 191 MB | FP16 | NPU |  [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.so) 
+
 
 
 ## Installation
@@ -95,9 +100,28 @@ device. This script does the following:
 python -m qai_hub_models.models.whisper_small_en.export
 ```
 
+```
+Profile Job summary of WhisperEncoder
+--------------------------------------------------
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 1682.16 ms
+Estimated Peak Memory Range: 0.92-0.92 MB
+Compute Units: NPU (1473) | Total (1473)
+
+Profile Job summary of WhisperDecoder
+--------------------------------------------------
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 20.40 ms
+Estimated Peak Memory Range: 121.48-121.48 MB
+Compute Units: NPU (2255) | Total (2255)
+
+
+```
+
+
 ## How does this work?
 
-This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/Whisper-Small-En/export.py)
+This [export script](https://aihub.qualcomm.com/models/whisper_small_en/qai_hub_models/models/Whisper-Small-En/export.py)
 leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
 on-device. Lets go through each step below in detail:
 
@@ -175,6 +199,7 @@ AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
 
 
 
+
 ## Deploying compiled model to Android
 
 
@@ -196,7 +221,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 ## License
 - The license for the original implementation of Whisper-Small-En can be found
   [here](https://github.com/openai/whisper/blob/main/LICENSE).
-- The license for the compiled assets for on-device deployment can be found [here]({deploy_license_url})
+- 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)
 
 ## References
 * [Robust Speech Recognition via Large-Scale Weak Supervision](https://cdn.openai.com/papers/whisper.pdf)