v0.45.0

See https://github.com/quic/ai-hub-models/releases/v0.45.0 for changelog.

README.md

@@ -10,57 +10,35 @@ pipeline_tag: automatic-speech-recognition
 
 ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/web-assets/model_demo.png)
 
-# Whisper-Base: Optimized for Qualcomm Devices
+# Whisper-Base: 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 is based on the implementation of Whisper-Base found [here](https://github.com/huggingface/transformers/tree/v4.42.3/src/transformers/models/whisper). This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/whisper_base) library to export with custom configurations. More details on model performance
-across various devices, can be found [here](#performance-summary).
-
-Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
-
-
-
-## Getting Started
-
-There are two ways to deploy this model on your device:
-
-### Option 1: Download Pre-Exported Models
-
-Download the pre-exported model assets directly from:
-- **This repository**: Use the model files available in the Files tab above
-- **[Whisper-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_base)**: Browse device-specific assets and performance metrics
 
-These pre-exported models are ready to integrate into your application using TensorFlow Lite, ONNX Runtime, or Qualcomm AI Engine Direct.
-
-### Option 2: Export with Custom Configurations
+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.
 
-Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/whisper_base) Python library to compile and export the model with your own:
-- Custom weights (e.g., fine-tuned checkpoints)
-- Custom input shapes
-- Target device and runtime configurations
+This model is an implementation of Whisper-Base found [here](https://github.com/huggingface/transformers/tree/v4.42.3/src/transformers/models/whisper).
 
-This option is ideal if you need to customize the model beyond the default configuration provided here.
 
-See our repository for [Whisper-Base on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/whisper_base) for usage instructions.
+This repository provides scripts to run Whisper-Base on Qualcomm® devices.
+More details on model performance across various devices, can be found
+[here](https://aihub.qualcomm.com/models/whisper_base).
 
 
-## Model Details
 
-**Model Type:** Model_use_case.speech_recognition
+### Model Details
 
-**Model Stats:**
-- Model checkpoint: openai/whisper-base
-- Input resolution: 80x3000 (30 seconds audio)
-- Max decoded sequence length: 200 tokens
-- Number of parameters (HfWhisperEncoder): 23.7M
-- Model size (HfWhisperEncoder) (float): 90.7 MB
-- Number of parameters (HfWhisperDecoder): 48.9M
-- Model size (HfWhisperDecoder) (float): 187 MB
+- **Model Type:** Model_use_case.speech_recognition
+- **Model Stats:**
+  - Model checkpoint: openai/whisper-base
+  - Input resolution: 80x3000 (30 seconds audio)
+  - Max decoded sequence length: 200 tokens
+  - Number of parameters (HfWhisperEncoder): 23.7M
+  - Model size (HfWhisperEncoder) (float): 90.7 MB
+  - Number of parameters (HfWhisperDecoder): 48.9M
+  - Model size (HfWhisperDecoder) (float): 187 MB
 
-## Performance Summary
 | 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 | 123.343 ms | 1 - 10 MB | NPU | Use Export Script |
 | HfWhisperEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_CONTEXT_BINARY | 99.511 ms | 0 - 22 MB | NPU | Use Export Script |
 | HfWhisperEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 37.269 ms | 0 - 4 MB | NPU | Use Export Script |
@@ -94,14 +72,178 @@ See our repository for [Whisper-Base on GitHub](https://github.com/quic/ai-hub-m
 | HfWhisperDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 3.416 ms | 20 - 20 MB | NPU | Use Export Script |
 | HfWhisperDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 3.457 ms | 126 - 126 MB | NPU | Use Export Script |
 
+
+
+
+## Installation
+
+
+Install the package via pip:
+```bash
+# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
+pip install "qai-hub-models[whisper-base]"
+```
+
+
+## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
+
+Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.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://workbench.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_base.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_base.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_base.export
+```
+
+
+
+## How does this work?
+
+This [export script](https://aihub.qualcomm.com/models/whisper_base/qai_hub_models/models/Whisper-Base/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_base import Model
+
+# Load the model
+torch_model = Model.from_pretrained()
+
+# Device
+device = hub.Device("Samsung Galaxy S25")
+
+# 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 Workbench. [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-Base's performance across various devices [here](https://aihub.qualcomm.com/models/whisper_base).
+Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
+
+
 ## License
 * The license for the original implementation of Whisper-Base can be found
   [here](https://github.com/huggingface/transformers/blob/v4.42.3/LICENSE).
 
+
+
 ## 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).
+* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
+
+

precompiled/qualcomm-qcs8275-proxy/Whisper-Base_HfWhisperDecoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2af409fcf2fadc4a83af86289e898ade1ac7fb2a70bc3eb83ff021a49844ef
+size 151859200

precompiled/qualcomm-qcs8275-proxy/Whisper-Base_HfWhisperEncoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bef58f29df12ec9183254b830fcdb20a28897a6d47170f3e8255e1650d2154e
+size 49549312

precompiled/qualcomm-qcs8275-proxy/tool-versions.yaml

@@ -0,0 +1,3 @@
+tool_versions:
+  qnn_context_binary:
+    qairt: 2.41.0.251128145156_191518-auto

precompiled/qualcomm-qcs8450-proxy/Whisper-Base_HfWhisperDecoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed1d5de7dc70310c2b82d94d4ff5d1e9bc3590c507d102457010c890e533f96
+size 151318528

precompiled/qualcomm-qcs8450-proxy/Whisper-Base_HfWhisperEncoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f936c81a41043f5fb806d581fc6a6603df47f50d62c15456239415997c0173
+size 48820224

precompiled/qualcomm-qcs8450-proxy/tool-versions.yaml

@@ -0,0 +1,3 @@
+tool_versions:
+  qnn_context_binary:
+    qairt: 2.41.0.251128145156_191518

precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperDecoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c243eb43b70c414ae21bd4269ab8fb8f95668b79ab39028ddb76398a9aa4824
+size 151855104

precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperDecoder_float.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684b351dd1e33034d664903807443cfd5c7078b2690eafa829d8d9b727adfa5b
+size 137234777

precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperEncoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c26c8ce5a03d4a9fcc52956ed34771f2bad89c6b4daf11b2e7a8a2e55376698
+size 49577984

precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperEncoder_float.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ad23e99b6e23e3d4464b0c53e1e55cc101d2f46142f725902125a15b72483f
+size 47020169

precompiled/qualcomm-qcs8550-proxy/tool-versions.yaml

@@ -0,0 +1,4 @@
+tool_versions:
+  precompiled_qnn_onnx:
+    qairt: 2.37.1.250807093845_124904
+    onnx_runtime: 1.23.0

precompiled/qualcomm-qcs9075-proxy/Whisper-Base_HfWhisperDecoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b5bb55cac839ad58cf791ad30f1f13dea58838e8459154432e94357cff98b2
+size 151855104

precompiled/qualcomm-qcs9075-proxy/Whisper-Base_HfWhisperEncoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c9c12ead76b4634eeaee77c422218c699387d084def53ca183cbb9025453f93
+size 49590272

precompiled/qualcomm-qcs9075-proxy/tool-versions.yaml

@@ -0,0 +1,3 @@
+tool_versions:
+  qnn_context_binary:
+    qairt: 2.41.0.251128145156_191518-auto

precompiled/qualcomm-sa7255p/Whisper-Base_HfWhisperDecoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e2af409fcf2fadc4a83af86289e898ade1ac7fb2a70bc3eb83ff021a49844ef
+size 151859200

precompiled/qualcomm-sa7255p/Whisper-Base_HfWhisperEncoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bef58f29df12ec9183254b830fcdb20a28897a6d47170f3e8255e1650d2154e
+size 49549312

precompiled/qualcomm-sa7255p/tool-versions.yaml

@@ -0,0 +1,3 @@
+tool_versions:
+  qnn_context_binary:
+    qairt: 2.41.0.251128145156_191518-auto

precompiled/qualcomm-sa8295p/Whisper-Base_HfWhisperDecoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8dcda98901eebd5108419ecdd034ebd37a5a60f88ea2e5833da535551364ad
+size 151306240

precompiled/qualcomm-sa8295p/Whisper-Base_HfWhisperEncoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f497cb6529965403bb4059a3d79d035cc7d5a90275b897bcab70d6c3675bcd
+size 48820224

precompiled/qualcomm-sa8295p/tool-versions.yaml

@@ -0,0 +1,3 @@
+tool_versions:
+  qnn_context_binary:
+    qairt: 2.41.0.251128145156_191518-auto

precompiled/qualcomm-sa8775p/Whisper-Base_HfWhisperDecoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b5bb55cac839ad58cf791ad30f1f13dea58838e8459154432e94357cff98b2
+size 151855104

precompiled/qualcomm-sa8775p/Whisper-Base_HfWhisperEncoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c9c12ead76b4634eeaee77c422218c699387d084def53ca183cbb9025453f93
+size 49590272

precompiled/qualcomm-sa8775p/tool-versions.yaml

@@ -0,0 +1,3 @@
+tool_versions:
+  qnn_context_binary:
+    qairt: 2.41.0.251128145156_191518-auto

precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperDecoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484b77d368ef55976067da15578a05707d0c4a8eef400a940849cf0758f14c55
+size 151834624

precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperDecoder_float.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5565613b4b24bae28b69d27b57f72b4165c493c0b70b643493d1707ad5329f39
+size 137226217

precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperEncoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a3509858ba7aa8bcf618ccf351dea2f5e9d496a11440a24aab6654b9e2fc6f
+size 49602560

precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperEncoder_float.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138bbceb4a3ef59853ac568c0763644736df3b46c52d6719faa5c10875491d49
+size 46951764

precompiled/qualcomm-snapdragon-8-elite-for-galaxy/tool-versions.yaml

@@ -0,0 +1,4 @@
+tool_versions:
+  precompiled_qnn_onnx:
+    qairt: 2.37.1.250807093845_124904
+    onnx_runtime: 1.23.0

precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperDecoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24209ad2564bafde0e95411dec2adf1682ddaf09f46590c19a0a162f85a4c193
+size 152010752

precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperDecoder_float.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb3d2e9fe673705c7a43addafc5d2a3d422f27aead3322b8145e995a1cb4405
+size 137271921

precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperEncoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82bebc63b61caf63aac5fbf93deca4c1cf893528b46db34b8448ae27abfec33f
+size 49795072

precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperEncoder_float.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da25b20b81b6e2961cb5ee10c79da362d20d2c07e9e29c36c6c3813b2762b71
+size 46981315

precompiled/qualcomm-snapdragon-8-elite-gen5/tool-versions.yaml

@@ -0,0 +1,4 @@
+tool_versions:
+  precompiled_qnn_onnx:
+    qairt: 2.37.1.250807093845_124904
+    onnx_runtime: 1.23.0

precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperDecoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c7b62d3e89cf544c5f83f2b78e46ac4ca4e3a90aaf2601da07067f08f1fe55
+size 151855104

precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperDecoder_float.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618053a260b37693cd685d6ea8e23ae3c83fe75769ad0506fe3aa038b59898d0
+size 137235674

precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperEncoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d424aa9539ee890561cc1e37c8d5f4c0bd6f2054fb4303a1da4282615225278c
+size 49582080

precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperEncoder_float.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7d4af2e9a2ad5857c9f256fa94f1c9815cdd2fcda3cb11ce0f3cc0408752d0
+size 47041474

precompiled/qualcomm-snapdragon-8gen3/tool-versions.yaml

@@ -0,0 +1,4 @@
+tool_versions:
+  precompiled_qnn_onnx:
+    qairt: 2.37.1.250807093845_124904
+    onnx_runtime: 1.23.0

precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperDecoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d84b7034c71c0a99ba3f75f7ba08e9a2e646ed6f4e10cd8a24ce0ac873ea5942
+size 151855104

precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperDecoder_float.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f6823dc292b15f4e172f8d5e6de205ad769ae5ee7f0a21b5f573522463731a
+size 137232366

precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperEncoder_float.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb3c4190fe6e689ffbc0c468303b0e8f4be4f3df37d6e9c9a033988584e648e
+size 49577984

precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperEncoder_float.onnx.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2864717505d7841d606b799b5d5da05770b93f64164e7e029bea6f5c5594c3
+size 47012891

precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml

@@ -0,0 +1,4 @@
+tool_versions:
+  precompiled_qnn_onnx:
+    qairt: 2.37.1.250807093845_124904
+    onnx_runtime: 1.23.0