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 | 608.885 ms | 80 - 511 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 | 25.793 ms | 16 - 19 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 | 1873.577 ms | 0 - 226 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 | 12.151 ms | 61 - 130 MB | FP16 | NPU |  [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 623.35 ms | 97 - 531 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 | 54.275 ms | 122 - 125 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 | 1890.126 ms | 0 - 243 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 | 11.949 ms | 61 - 128 MB | FP16 | NPU |  [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.so) 
 
 
 
@@ -103,16 +103,16 @@ python -m qai_hub_models.models.whisper_small_en.export
 ```
 Profile Job summary of WhisperEncoder
 --------------------------------------------------
-Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 1882.60 ms
-Estimated Peak Memory Range: 0.52-223.35 MB
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 1087.18 ms
+Estimated Peak Memory Range: 0.46-0.46 MB
 Compute Units: NPU (1329) | Total (1329)
 
 Profile Job summary of WhisperDecoder
 --------------------------------------------------
-Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 11.79 ms
-Estimated Peak Memory Range: 60.69-127.91 MB
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 10.68 ms
+Estimated Peak Memory Range: 60.75-60.75 MB
 Compute Units: NPU (2255) | Total (2255)
 
 
@@ -134,29 +134,49 @@ in memory using the `jit.trace` and then call the `submit_compile_job` API.
 import torch
 
 import qai_hub as hub
-from qai_hub_models.models.whisper_small_en import Model
+from qai_hub_models.models.whisper_small_en import WhisperEncoder,WhisperDecoder
 
 # Load the model
-torch_model = Model.from_pretrained()
+encoder_model = WhisperEncoder.from_pretrained()
+
+decoder_model = WhisperDecoder.from_pretrained()
+
 
 # Device
 device = hub.Device("Samsung Galaxy S23")
 
+
 # Trace model
-input_shape = torch_model.get_input_spec()
-sample_inputs = torch_model.sample_inputs()
+encoder_input_shape = encoder_model.get_input_spec()
+encoder_sample_inputs = encoder_model.sample_inputs()
 
-pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
+traced_encoder_model = torch.jit.trace(encoder_model, [torch.tensor(data[0]) for _, data in encoder_sample_inputs.items()])
 
 # Compile model on a specific device
-compile_job = hub.submit_compile_job(
-    model=pt_model,
+encoder_compile_job = hub.submit_compile_job(
+    model=traced_encoder_model ,
     device=device,
-    input_specs=torch_model.get_input_spec(),
+    input_specs=encoder_model.get_input_spec(),
 )
 
 # Get target model to run on-device
-target_model = compile_job.get_target_model()
+encoder_target_model = encoder_compile_job.get_target_model()
+
+# Trace model
+decoder_input_shape = decoder_model.get_input_spec()
+decoder_sample_inputs = decoder_model.sample_inputs()
+
+traced_decoder_model = torch.jit.trace(decoder_model, [torch.tensor(data[0]) for _, data in decoder_sample_inputs.items()])
+
+# Compile model on a specific device
+decoder_compile_job = hub.submit_compile_job(
+    model=traced_decoder_model ,
+    device=device,
+    input_specs=decoder_model.get_input_spec(),
+)
+
+# Get target model to run on-device
+decoder_target_model = decoder_compile_job.get_target_model()
 
 ```
 
@@ -168,10 +188,16 @@ After compiling models from step 1. Models can be profiled model on-device using
 provisioned in the cloud.  Once the job is submitted, you can navigate to a
 provided job URL to view a variety of on-device performance metrics.
 ```python
-profile_job = hub.submit_profile_job(
-    model=target_model,
-    device=device,
-)
+
+encoder_profile_job = hub.submit_profile_job(
+        model=encoder_target_model,
+        device=device,
+        )       
+
+decoder_profile_job = hub.submit_profile_job(
+        model=decoder_target_model,
+        device=device,
+        )       
 
 ```
 
@@ -180,14 +206,20 @@ Step 3: **Verify on-device accuracy**
 To verify the accuracy of the model on-device, you can run on-device inference
 on sample input data on the same cloud hosted device.
 ```python
-input_data = torch_model.sample_inputs()
-inference_job = hub.submit_inference_job(
-    model=target_model,
-    device=device,
-    inputs=input_data,
-)
-
-on_device_output = inference_job.download_output_data()
+encoder_input_data = encoder_model.sample_inputs()
+encoder_inference_job = hub.submit_inference_job(
+        model=encoder_target_model,
+        device=device,
+        inputs=encoder_input_data,
+    )
+encoder_inference_job.download_output_data()
+decoder_input_data = decoder_model.sample_inputs()
+decoder_inference_job = hub.submit_inference_job(
+        model=decoder_target_model,
+        device=device,
+        inputs=decoder_input_data,
+    )
+decoder_inference_job.download_output_data()
 
 ```
 With the output of the model, you can compute like PSNR, relative errors or