diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..bd658acccea2f60bd442576cef35075b5d9dc97c 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
diff --git a/DEPLOYMENT_MODEL_LICENSE.pdf b/DEPLOYMENT_MODEL_LICENSE.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..42699872aa2347c5837d291559bcd5eaa302b7ea
--- /dev/null
+++ b/DEPLOYMENT_MODEL_LICENSE.pdf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
+size 109629
diff --git a/LICENSE b/LICENSE
new file mode 100644
index 0000000000000000000000000000000000000000..698c1c0c019be1401276a8b21e1cabd82223a56a
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,2 @@
+The license of the original trained model can be found at https://github.com/huggingface/transformers/blob/v4.42.3/LICENSE.
+The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..fba81d9f3263499aed526b33e1dfc4307155016b
--- /dev/null
+++ b/README.md
@@ -0,0 +1,251 @@
+---
+library_name: pytorch
+license: other
+tags:
+- foundation
+- android
+pipeline_tag: automatic-speech-recognition
+
+---
+
+![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/web-assets/model_demo.png)
+
+# Whisper-Small: Optimized for Mobile Deployment
+## Transformer-based automatic speech recognition (ASR) model for multilingual transcription and translation available on HuggingFace
+
+
+HuggingFace Whisper-Small ASR (Automatic Speech Recognition) model is a state-of-the-art system designed for transcribing spoken language into written text. This model is based on the transformer architecture and has been optimized for edge inference by replacing Multi-Head Attention (MHA) with Single-Head Attention (SHA) and linear layers with convolutional (conv) layers. It exhibits robust performance in realistic, noisy environments, making it highly reliable for real-world applications. Specifically, it excels in long-form transcription, capable of accurately transcribing audio clips up to 30 seconds long. Time to the first token is the encoder's latency, while time to each additional token is decoder's latency, where we assume a max decoded length specified below.
+
+This model is an implementation of Whisper-Small found [here](https://github.com/huggingface/transformers/tree/v4.42.3/src/transformers/models/whisper).
+
+
+This repository provides scripts to run Whisper-Small on Qualcomm® devices.
+More details on model performance across various devices, can be found
+[here](https://aihub.qualcomm.com/models/whisper_small).
+
+
+
+### Model Details
+
+- **Model Type:** Model_use_case.speech_recognition
+- **Model Stats:**
+  - Model checkpoint: openai/whisper-small
+  - Input resolution: 80x3000 (30 seconds audio)
+  - Max decoded sequence length: 200 tokens
+  - Number of parameters (HfWhisperEncoder): 102M
+  - Model size (HfWhisperEncoder) (float): 391 MB
+  - Number of parameters (HfWhisperDecoder): 139M
+  - Model size (HfWhisperDecoder) (float): 533 MB
+
+| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| HfWhisperEncoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 424.037 ms | 1 - 10 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_CONTEXT_BINARY | 314.877 ms | 0 - 18 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 132.256 ms | 8 - 10 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 154.294 ms | 1 - 10 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 424.037 ms | 1 - 10 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 136.109 ms | 1 - 3 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_CONTEXT_BINARY | 241.55 ms | 0 - 17 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 138.032 ms | 1 - 3 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 154.294 ms | 1 - 10 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 134.534 ms | 1 - 3 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 138.173 ms | 0 - 258 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 102.365 ms | 0 - 19 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 105.447 ms | 128 - 147 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 86.361 ms | 0 - 14 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 89.991 ms | 129 - 143 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 130.698 ms | 0 - 0 MB | NPU | Use Export Script |
+| HfWhisperEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 131.817 ms | 227 - 227 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 18.261 ms | 45 - 54 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_CONTEXT_BINARY | 17.513 ms | 52 - 73 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 12.24 ms | 53 - 55 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 13.211 ms | 45 - 55 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 18.261 ms | 45 - 54 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 11.863 ms | 66 - 68 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_CONTEXT_BINARY | 14.789 ms | 58 - 73 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 11.818 ms | 64 - 66 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 13.211 ms | 45 - 55 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_CONTEXT_BINARY | 12.05 ms | 65 - 69 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | PRECOMPILED_QNN_ONNX | 13.294 ms | 0 - 319 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 9.634 ms | 55 - 74 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 10.846 ms | 75 - 95 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 8.157 ms | 60 - 75 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | PRECOMPILED_QNN_ONNX | 8.731 ms | 73 - 87 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 10.432 ms | 60 - 60 MB | NPU | Use Export Script |
+| HfWhisperDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 10.429 ms | 286 - 286 MB | NPU | Use Export Script |
+
+
+
+
+## Installation
+
+
+Install the package via pip:
+```bash
+pip install "qai-hub-models[whisper-small]"
+```
+
+
+## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
+
+Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
+Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
+
+With this API token, you can configure your client to run models on the cloud
+hosted devices.
+```bash
+qai-hub configure --api_token API_TOKEN
+```
+Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
+
+
+
+## Demo off target
+
+The package contains a simple end-to-end demo that downloads pre-trained
+weights and runs this model on a sample input.
+
+```bash
+python -m qai_hub_models.models.whisper_small.demo
+```
+
+The above demo runs a reference implementation of pre-processing, model
+inference, and post processing.
+
+**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
+environment, please add the following to your cell (instead of the above).
+```
+%run -m qai_hub_models.models.whisper_small.demo
+```
+
+
+### Run model on a cloud-hosted device
+
+In addition to the demo, you can also run the model on a cloud-hosted Qualcomm®
+device. This script does the following:
+* Performance check on-device on a cloud-hosted device
+* Downloads compiled assets that can be deployed on-device for Android.
+* Accuracy check between PyTorch and on-device outputs.
+
+```bash
+python -m qai_hub_models.models.whisper_small.export
+```
+
+
+
+## How does this work?
+
+This [export script](https://aihub.qualcomm.com/models/whisper_small/qai_hub_models/models/Whisper-Small/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:
+
+Step 1: **Compile model for on-device deployment**
+
+To compile a PyTorch model for on-device deployment, we first trace the model
+in memory using the `jit.trace` and then call the `submit_compile_job` API.
+
+```python
+import torch
+
+import qai_hub as hub
+from qai_hub_models.models.whisper_small import Model
+
+# Load the model
+torch_model = Model.from_pretrained()
+
+# Device
+device = hub.Device("Samsung Galaxy S24")
+
+# Trace model
+input_shape = torch_model.get_input_spec()
+sample_inputs = torch_model.sample_inputs()
+
+pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
+
+# Compile model on a specific device
+compile_job = hub.submit_compile_job(
+    model=pt_model,
+    device=device,
+    input_specs=torch_model.get_input_spec(),
+)
+
+# Get target model to run on-device
+target_model = compile_job.get_target_model()
+
+```
+
+
+Step 2: **Performance profiling on cloud-hosted device**
+
+After compiling models from step 1. Models can be profiled model on-device using the
+`target_model`. Note that this scripts runs the model on a device automatically
+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,
+)
+        
+```
+
+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()
+
+```
+With the output of the model, you can compute like PSNR, relative errors or
+spot check the output with expected output.
+
+**Note**: This on-device profiling and inference requires access to Qualcomm®
+AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
+
+
+
+
+## Deploying compiled model to Android
+
+
+The models can be deployed using multiple runtimes:
+- TensorFlow Lite (`.tflite` export): [This
+  tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a
+  guide to deploy the .tflite model in an Android application.
+
+
+- QNN (`.so` export ): This [sample
+  app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html)
+provides instructions on how to use the `.so` shared library  in an Android application.
+
+
+## View on Qualcomm® AI Hub
+Get more details on Whisper-Small's performance across various devices [here](https://aihub.qualcomm.com/models/whisper_small).
+Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
+
+
+## License
+* The license for the original implementation of Whisper-Small can be found
+  [here](https://github.com/huggingface/transformers/blob/v4.42.3/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)
+
+
+
+## References
+* [Robust Speech Recognition via Large-Scale Weak Supervision](https://cdn.openai.com/papers/whisper.pdf)
+* [Source Model Implementation](https://github.com/huggingface/transformers/tree/v4.42.3/src/transformers/models/whisper)
+
+
+
+## Community
+* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
+* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
+
+
diff --git a/precompiled/qualcomm-qcs8275-proxy/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-qcs8275-proxy/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b1dd8c0ad44e7746ceaf4e054c483af9d2f855ca
--- /dev/null
+++ b/precompiled/qualcomm-qcs8275-proxy/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1346f897406292a6b55a7d357c4c2a2d910a892417fbc345bbff297c76f592c9
+size 361365504
diff --git a/precompiled/qualcomm-qcs8275-proxy/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-qcs8275-proxy/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c4c775fed1af1a00dc64f9057b5451f8d1158863
--- /dev/null
+++ b/precompiled/qualcomm-qcs8275-proxy/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26d547e17790a5766c5fe21dc3c108d0ef75ab0688c68622ea5476d752b26a5
+size 236208128
diff --git a/precompiled/qualcomm-qcs8275-proxy/sdk_versions.yml b/precompiled/qualcomm-qcs8275-proxy/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..cf3db9eb5c8793178dd19d986de2ebb9f7dee490
--- /dev/null
+++ b/precompiled/qualcomm-qcs8275-proxy/sdk_versions.yml
@@ -0,0 +1,3 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859-auto
diff --git a/precompiled/qualcomm-qcs8450-proxy/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-qcs8450-proxy/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..7f04b4f1880cec193543d1ef2ac16c383a1d2263
--- /dev/null
+++ b/precompiled/qualcomm-qcs8450-proxy/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7afda73190825ccc28d685e0f69bd3c2f6f10d12c0f3e6ecbcda99f677107f
+size 359784448
diff --git a/precompiled/qualcomm-qcs8450-proxy/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-qcs8450-proxy/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ff6d6fad5be59a165024f191849c6393fe22369e
--- /dev/null
+++ b/precompiled/qualcomm-qcs8450-proxy/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aaf032a963e52d86a02bc8c64814165c194c9ba598f384e2596bb02a906028c
+size 218316800
diff --git a/precompiled/qualcomm-qcs8450-proxy/sdk_versions.yml b/precompiled/qualcomm-qcs8450-proxy/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..645a4ba899019438314a76813152c259f4f74b92
--- /dev/null
+++ b/precompiled/qualcomm-qcs8450-proxy/sdk_versions.yml
@@ -0,0 +1,3 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859
diff --git a/precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6c9d8353dc7c3960e3a4b4d813fc48899a2cdb3d
--- /dev/null
+++ b/precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53306e6d2f5c950cff0d325a24ae9d804259c0a7edaa92ebd6181fbbe0b77768
+size 361381888
diff --git a/precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..11bc09beedc183b982bee909fab26b3227a38178
--- /dev/null
+++ b/precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ec48372bff0de0dbec0b6e49195c310805e076e6841fa1b4e9ab8b21e3eb90
+size 236367872
diff --git a/precompiled/qualcomm-qcs8550-proxy/sdk_versions.yml b/precompiled/qualcomm-qcs8550-proxy/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..645a4ba899019438314a76813152c259f4f74b92
--- /dev/null
+++ b/precompiled/qualcomm-qcs8550-proxy/sdk_versions.yml
@@ -0,0 +1,3 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859
diff --git a/precompiled/qualcomm-qcs9075-proxy/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-qcs9075-proxy/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cc81edcf2523cafef6ba6fe86a88d751f84569b6
--- /dev/null
+++ b/precompiled/qualcomm-qcs9075-proxy/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a15e38e74a05b1d84629f15b9840d2c26b09ff31de6f7e727a4afdc229fa26
+size 361373696
diff --git a/precompiled/qualcomm-qcs9075-proxy/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-qcs9075-proxy/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..71e091ce811066eb95f00fda504bc0dc622f4237
--- /dev/null
+++ b/precompiled/qualcomm-qcs9075-proxy/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c05d154d45081caa703f8e0a33a64f2e00dd954ae95cd6aaed5e7129e21e2b
+size 236154880
diff --git a/precompiled/qualcomm-qcs9075-proxy/sdk_versions.yml b/precompiled/qualcomm-qcs9075-proxy/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..cf3db9eb5c8793178dd19d986de2ebb9f7dee490
--- /dev/null
+++ b/precompiled/qualcomm-qcs9075-proxy/sdk_versions.yml
@@ -0,0 +1,3 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859-auto
diff --git a/precompiled/qualcomm-sa7255p/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-sa7255p/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b1dd8c0ad44e7746ceaf4e054c483af9d2f855ca
--- /dev/null
+++ b/precompiled/qualcomm-sa7255p/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1346f897406292a6b55a7d357c4c2a2d910a892417fbc345bbff297c76f592c9
+size 361365504
diff --git a/precompiled/qualcomm-sa7255p/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-sa7255p/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c4c775fed1af1a00dc64f9057b5451f8d1158863
--- /dev/null
+++ b/precompiled/qualcomm-sa7255p/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26d547e17790a5766c5fe21dc3c108d0ef75ab0688c68622ea5476d752b26a5
+size 236208128
diff --git a/precompiled/qualcomm-sa7255p/sdk_versions.yml b/precompiled/qualcomm-sa7255p/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..cf3db9eb5c8793178dd19d986de2ebb9f7dee490
--- /dev/null
+++ b/precompiled/qualcomm-sa7255p/sdk_versions.yml
@@ -0,0 +1,3 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859-auto
diff --git a/precompiled/qualcomm-sa8255p-proxy/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-sa8255p-proxy/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6c9d8353dc7c3960e3a4b4d813fc48899a2cdb3d
--- /dev/null
+++ b/precompiled/qualcomm-sa8255p-proxy/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53306e6d2f5c950cff0d325a24ae9d804259c0a7edaa92ebd6181fbbe0b77768
+size 361381888
diff --git a/precompiled/qualcomm-sa8255p-proxy/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-sa8255p-proxy/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..11bc09beedc183b982bee909fab26b3227a38178
--- /dev/null
+++ b/precompiled/qualcomm-sa8255p-proxy/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ec48372bff0de0dbec0b6e49195c310805e076e6841fa1b4e9ab8b21e3eb90
+size 236367872
diff --git a/precompiled/qualcomm-sa8255p-proxy/sdk_versions.yml b/precompiled/qualcomm-sa8255p-proxy/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..645a4ba899019438314a76813152c259f4f74b92
--- /dev/null
+++ b/precompiled/qualcomm-sa8255p-proxy/sdk_versions.yml
@@ -0,0 +1,3 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859
diff --git a/precompiled/qualcomm-sa8295p/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-sa8295p/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cfcf54e30dc12a5511c7832c6b905f65b8278fa1
--- /dev/null
+++ b/precompiled/qualcomm-sa8295p/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281884ee7572dab3d1b60878bb05cbd13313349830fc763976ea221124034f31
+size 359763968
diff --git a/precompiled/qualcomm-sa8295p/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-sa8295p/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..af909128abb76d12a3a3b278f2f0c3374b93b309
--- /dev/null
+++ b/precompiled/qualcomm-sa8295p/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baef055864bfcf84f2217aee0e3af4ef51d7072d1c2eaae91757de01d20bd84e
+size 218382336
diff --git a/precompiled/qualcomm-sa8295p/sdk_versions.yml b/precompiled/qualcomm-sa8295p/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..cf3db9eb5c8793178dd19d986de2ebb9f7dee490
--- /dev/null
+++ b/precompiled/qualcomm-sa8295p/sdk_versions.yml
@@ -0,0 +1,3 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859-auto
diff --git a/precompiled/qualcomm-sa8650p-proxy/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-sa8650p-proxy/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6c9d8353dc7c3960e3a4b4d813fc48899a2cdb3d
--- /dev/null
+++ b/precompiled/qualcomm-sa8650p-proxy/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53306e6d2f5c950cff0d325a24ae9d804259c0a7edaa92ebd6181fbbe0b77768
+size 361381888
diff --git a/precompiled/qualcomm-sa8650p-proxy/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-sa8650p-proxy/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..11bc09beedc183b982bee909fab26b3227a38178
--- /dev/null
+++ b/precompiled/qualcomm-sa8650p-proxy/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ec48372bff0de0dbec0b6e49195c310805e076e6841fa1b4e9ab8b21e3eb90
+size 236367872
diff --git a/precompiled/qualcomm-sa8650p-proxy/sdk_versions.yml b/precompiled/qualcomm-sa8650p-proxy/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..645a4ba899019438314a76813152c259f4f74b92
--- /dev/null
+++ b/precompiled/qualcomm-sa8650p-proxy/sdk_versions.yml
@@ -0,0 +1,3 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859
diff --git a/precompiled/qualcomm-sa8775p/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-sa8775p/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..cc81edcf2523cafef6ba6fe86a88d751f84569b6
--- /dev/null
+++ b/precompiled/qualcomm-sa8775p/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a15e38e74a05b1d84629f15b9840d2c26b09ff31de6f7e727a4afdc229fa26
+size 361373696
diff --git a/precompiled/qualcomm-sa8775p/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-sa8775p/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..71e091ce811066eb95f00fda504bc0dc622f4237
--- /dev/null
+++ b/precompiled/qualcomm-sa8775p/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8c05d154d45081caa703f8e0a33a64f2e00dd954ae95cd6aaed5e7129e21e2b
+size 236154880
diff --git a/precompiled/qualcomm-sa8775p/sdk_versions.yml b/precompiled/qualcomm-sa8775p/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..cf3db9eb5c8793178dd19d986de2ebb9f7dee490
--- /dev/null
+++ b/precompiled/qualcomm-sa8775p/sdk_versions.yml
@@ -0,0 +1,3 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859-auto
diff --git a/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..90e27c89bcd6f6e28fe33efee268af3efd45bce1
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e71d51459e66cb1c9127328c4a160d3606f54abbb74b42c4ead7f39b42f38f
+size 361291776
diff --git a/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperDecoder.onnx.zip b/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperDecoder.onnx.zip
new file mode 100644
index 0000000000000000000000000000000000000000..9866c6fb13dc393db504fd52dc573fbb39822bda
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperDecoder.onnx.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e6f9e7608a66b9f1d3af0659f51441e5686b403097d368a56f14c7ed9603607
+size 330432535
diff --git a/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..b86e915ecfb793555ab73aa45ec527a7ee5537c5
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a20824548619ee0fd9eec6878c03bc27655e4eabf9f68b39995b3f1acc7ad1a
+size 235958272
diff --git a/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperEncoder.onnx.zip b/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperEncoder.onnx.zip
new file mode 100644
index 0000000000000000000000000000000000000000..f7d237af41c97015e5fbba2ae833ea06379ff492
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8-elite/Whisper-Small_HfWhisperEncoder.onnx.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4504dedf932f69c95aaa30df710e8bdce98787992fd4b6d5bf17d0a215c956ee
+size 196175657
diff --git a/precompiled/qualcomm-snapdragon-8-elite/sdk_versions.yml b/precompiled/qualcomm-snapdragon-8-elite/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..609bfba19166f29f971a2e5925e62115df03422c
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8-elite/sdk_versions.yml
@@ -0,0 +1,6 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859
+  precompiled_qnn_onnx:
+    qairt: 2.33.2.250410134701_117956
+    onnx_runtime: 1.22.0
diff --git a/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6c9d8353dc7c3960e3a4b4d813fc48899a2cdb3d
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53306e6d2f5c950cff0d325a24ae9d804259c0a7edaa92ebd6181fbbe0b77768
+size 361381888
diff --git a/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperDecoder.onnx.zip b/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperDecoder.onnx.zip
new file mode 100644
index 0000000000000000000000000000000000000000..a9cd2e720f4efc690c3d288d237fd597e36543b4
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperDecoder.onnx.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04c2fa55da6ceb37c9782f431b4d96e54e9b9566bf6cd2dbac2b7c1b5f61d00
+size 330469625
diff --git a/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..11bc09beedc183b982bee909fab26b3227a38178
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ec48372bff0de0dbec0b6e49195c310805e076e6841fa1b4e9ab8b21e3eb90
+size 236367872
diff --git a/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperEncoder.onnx.zip b/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperEncoder.onnx.zip
new file mode 100644
index 0000000000000000000000000000000000000000..80ee4d9719920377a6c6b756075bf91714f52474
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8gen2/Whisper-Small_HfWhisperEncoder.onnx.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d8ff7c7f3d4b47231792485ba27b0504d97fed4ba7f63448404a71694648799
+size 197747935
diff --git a/precompiled/qualcomm-snapdragon-8gen2/sdk_versions.yml b/precompiled/qualcomm-snapdragon-8gen2/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..609bfba19166f29f971a2e5925e62115df03422c
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8gen2/sdk_versions.yml
@@ -0,0 +1,6 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859
+  precompiled_qnn_onnx:
+    qairt: 2.33.2.250410134701_117956
+    onnx_runtime: 1.22.0
diff --git a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..fef36592df475751ebee40f7494da31afa55d1f7
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d8322fe098b359133915828e93a36b51f77edeaa428d194cea1989f484ae0a7
+size 361369600
diff --git a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperDecoder.onnx.zip b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperDecoder.onnx.zip
new file mode 100644
index 0000000000000000000000000000000000000000..e68a6e98896b4f536252c93392b335e55a542f94
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperDecoder.onnx.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d668ec279ebd2a01525fd320e389fb140b31d1cdc5490cc31fc971de436935e
+size 330472065
diff --git a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..85c97602f1aa1138568f6e77c5c6f69810d1abaa
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6cbc6d2ed3b1ae7c674230937ff8a3bb3d20b2cbfa27c48e24958d8f9ba911f
+size 236478464
diff --git a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperEncoder.onnx.zip b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperEncoder.onnx.zip
new file mode 100644
index 0000000000000000000000000000000000000000..5747e3f4713c160b27244a0dcec738bc6fee33aa
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperEncoder.onnx.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e983757f38c492f2b54de9901d010de394eeda13cd07daa608466401838849b
+size 196723296
diff --git a/precompiled/qualcomm-snapdragon-8gen3/sdk_versions.yml b/precompiled/qualcomm-snapdragon-8gen3/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..609bfba19166f29f971a2e5925e62115df03422c
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-8gen3/sdk_versions.yml
@@ -0,0 +1,6 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859
+  precompiled_qnn_onnx:
+    qairt: 2.33.2.250410134701_117956
+    onnx_runtime: 1.22.0
diff --git a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperDecoder.bin b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperDecoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8ca3a626e10a3ca6fa3bc7be4c7acfae7c4f4efe
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperDecoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb7c14ab5f39b9cab50c29d5deb05f57fa130e52544fd18c9338e306707c566
+size 361385984
diff --git a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperDecoder.onnx.zip b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperDecoder.onnx.zip
new file mode 100644
index 0000000000000000000000000000000000000000..c0ee2f58ebb0401352691ca2bda6256122fc7b39
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperDecoder.onnx.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43425810d8d78355c30f3cffe5943904f7d36aa212c191ddacfdb22c3d28a6d9
+size 330473991
diff --git a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperEncoder.bin b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperEncoder.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4bbd6b8682e398cdcec0300808f8ebe3a0275e17
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperEncoder.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e53de4d1405ec58ade84b8edcd6dd5005394c6d7a78a7fb9c740e38fe92afc
+size 236400640
diff --git a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperEncoder.onnx.zip b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperEncoder.onnx.zip
new file mode 100644
index 0000000000000000000000000000000000000000..8f3e07eaf7955321c0e34d84faee03b6685ed008
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperEncoder.onnx.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e489759b13e47a1d158e16486785751334a3dfb3730d47b5787c651a5ee92e
+size 197739694
diff --git a/precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml b/precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml
new file mode 100644
index 0000000000000000000000000000000000000000..609bfba19166f29f971a2e5925e62115df03422c
--- /dev/null
+++ b/precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml
@@ -0,0 +1,6 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.37.0.250724175447_124859
+  precompiled_qnn_onnx:
+    qairt: 2.33.2.250410134701_117956
+    onnx_runtime: 1.22.0