diff --git a/DEPLOYMENT_MODEL_LICENSE.pdf b/DEPLOYMENT_MODEL_LICENSE.pdf deleted file mode 100644 index 42699872aa2347c5837d291559bcd5eaa302b7ea..0000000000000000000000000000000000000000 --- a/DEPLOYMENT_MODEL_LICENSE.pdf +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c -size 109629 diff --git a/LICENSE b/LICENSE index 698c1c0c019be1401276a8b21e1cabd82223a56a..a2a056017d99b57b1611b9022159cc3d3fcac2a5 100644 --- a/LICENSE +++ b/LICENSE @@ -1,2 +1 @@ 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 index 9c52c941f120d7b8701b48112811a3d4bad9587f..d2da009fd19c6fc501f1e5048ce40cf3eabd2020 100644 --- a/README.md +++ b/README.md @@ -10,245 +10,98 @@ 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 Mobile Deployment -## Transformer-based automatic speech recognition (ASR) model for multilingual transcription and translation available on HuggingFace - +# Whisper-Base: Optimized for Qualcomm Devices 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-Base found [here](https://github.com/huggingface/transformers/tree/v4.42.3/src/transformers/models/whisper). - - -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 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 | 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 | 122.517 ms | 1 - 11 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_CONTEXT_BINARY | 98.005 ms | 1 - 22 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 37.094 ms | 0 - 3 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 43.552 ms | 8 - 73 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 43.524 ms | 1 - 11 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 122.517 ms | 1 - 11 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 37.184 ms | 0 - 3 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_CONTEXT_BINARY | 75.209 ms | 1 - 17 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 37.08 ms | 1 - 3 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 43.524 ms | 1 - 11 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 26.734 ms | 1 - 19 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 34.136 ms | 41 - 60 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 18.158 ms | 0 - 14 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 23.994 ms | 38 - 53 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 15.238 ms | 0 - 12 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 22.515 ms | 38 - 49 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 37.481 ms | 0 - 0 MB | NPU | Use Export Script | -| HfWhisperEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 41.935 ms | 66 - 66 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 6.271 ms | 17 - 26 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_CONTEXT_BINARY | 5.153 ms | 20 - 41 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 3.987 ms | 20 - 22 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 4.53 ms | 0 - 142 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 4.711 ms | 19 - 29 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 6.271 ms | 17 - 26 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 3.925 ms | 17 - 19 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_CONTEXT_BINARY | 5.354 ms | 20 - 34 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 3.982 ms | 20 - 22 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 4.711 ms | 19 - 29 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 3.15 ms | 3 - 22 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 3.416 ms | 26 - 45 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 2.61 ms | 0 - 17 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 2.819 ms | 0 - 11 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 2.46 ms | 18 - 30 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 2.693 ms | 21 - 31 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 3.358 ms | 20 - 20 MB | NPU | Use Export Script | -| HfWhisperDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 3.416 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 -``` - +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). -### Run model on a cloud-hosted device +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. -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 -``` +## Getting Started +There are two ways to deploy this model on your device: -## How does this work? +### Option 1: Download Pre-Exported Models -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: +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 -Step 1: **Compile model for on-device deployment** +These pre-exported models are ready to integrate into your application using TensorFlow Lite, ONNX Runtime, or Qualcomm AI Engine Direct. -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. +### Option 2: Export with Custom Configurations -```python -import torch +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 -import qai_hub as hub -from qai_hub_models.models.whisper_base import Model +This option is ideal if you need to customize the model beyond the default configuration provided here. -# Load the model -torch_model = Model.from_pretrained() +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. -# Device -device = hub.Device("Samsung Galaxy S25") -# Trace model -input_shape = torch_model.get_input_spec() -sample_inputs = torch_model.sample_inputs() +## Model Details -pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()]) +**Model Type:** Model_use_case.speech_recognition -# 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/) +**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 | +| HfWhisperEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 43.713 ms | 7 - 73 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 43.597 ms | 1 - 10 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 123.343 ms | 1 - 10 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_CONTEXT_BINARY | 75.114 ms | 1 - 15 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 43.597 ms | 1 - 10 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 26.892 ms | 1 - 19 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 33.807 ms | 39 - 57 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 18.118 ms | 0 - 16 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 23.891 ms | 39 - 52 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | QNN_CONTEXT_BINARY | 15.21 ms | 0 - 11 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | PRECOMPILED_QNN_ONNX | 20.086 ms | 38 - 48 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 37.677 ms | 0 - 0 MB | NPU | Use Export Script | +| HfWhisperEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 42.065 ms | 67 - 67 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 6.352 ms | 20 - 29 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_CONTEXT_BINARY | 5.073 ms | 20 - 41 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 3.912 ms | 19 - 21 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 4.366 ms | 0 - 141 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 4.702 ms | 19 - 28 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 6.352 ms | 20 - 29 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_CONTEXT_BINARY | 5.363 ms | 20 - 34 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 4.702 ms | 19 - 28 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 3.133 ms | 0 - 19 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 3.414 ms | 25 - 44 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 2.591 ms | 0 - 13 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 2.917 ms | 0 - 14 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | QNN_CONTEXT_BINARY | 2.475 ms | 19 - 29 MB | NPU | Use Export Script | +| HfWhisperDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | PRECOMPILED_QNN_ONNX | 2.651 ms | 21 - 31 MB | NPU | Use Export Script | +| 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 | ## License * The license for the original implementation of Whisper-Base 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). - - +* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com). \ No newline at end of file diff --git a/precompiled/qualcomm-qcs8275-proxy/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-qcs8275-proxy/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index d777308bbc3050e6ae183d892fd01db9f9f1c331..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs8275-proxy/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:acc3f9971e6f17fc359ce48c01d40690bf2b9e9c36ea95faacdb72d6fd1d388d -size 151851008 diff --git a/precompiled/qualcomm-qcs8275-proxy/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-qcs8275-proxy/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index 8aa5bb89f37efecf645566aee06ca079e5ff911d..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs8275-proxy/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d2d1a746ed398611c5a751a9ec6a2c2263add2ae310250d7f95e8ce8a67dea63 -size 49537024 diff --git a/precompiled/qualcomm-qcs8275-proxy/tool-versions.yaml b/precompiled/qualcomm-qcs8275-proxy/tool-versions.yaml deleted file mode 100644 index 4cb4c03408f55902c17ea51b9b055908dfbcac32..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs8275-proxy/tool-versions.yaml +++ /dev/null @@ -1,3 +0,0 @@ -tool_versions: - qnn_context_binary: - qairt: 2.40.0.251030114326_189385-auto diff --git a/precompiled/qualcomm-qcs8450-proxy/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-qcs8450-proxy/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index beaa6ec54c23f2a954e4e8a4a970de91c4d5d0b4..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs8450-proxy/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:596f0bee0f19d656183579ee5b7db4867f3335a90ba5d6b9c6e432daa5f67009 -size 151318528 diff --git a/precompiled/qualcomm-qcs8450-proxy/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-qcs8450-proxy/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index 778f3b1500baeeb1950d43e01bc7f3d6ab7da01d..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs8450-proxy/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:507d7b891be49ba290e2c862c515bfc44d1e563b310b13123bb0ee5a3ffe5a1a -size 48816128 diff --git a/precompiled/qualcomm-qcs8450-proxy/tool-versions.yaml b/precompiled/qualcomm-qcs8450-proxy/tool-versions.yaml deleted file mode 100644 index dd8b2661f081194cd120bbfbfedc0d2de466fa2d..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs8450-proxy/tool-versions.yaml +++ /dev/null @@ -1,3 +0,0 @@ -tool_versions: - qnn_context_binary: - qairt: 2.40.0.251030114326_189385 diff --git a/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index ed6e929585f9ed8a6795dc38b666ccca048b5289..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:48ce8e1ee7f16a0aea384943b7630a623cc3dee61754eeb120b3e1a8c11ee1d8 -size 151846912 diff --git a/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperDecoder_float.onnx.zip b/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperDecoder_float.onnx.zip deleted file mode 100644 index 1ecb91a48c0e76040b54514ac0c81e8d03afa1a7..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperDecoder_float.onnx.zip +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4c6550061a1fbb8b0b5a65f62ebe91518aba6dda5e060b3d16ec1f4cbc4605f8 -size 137234763 diff --git a/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index c12b47176595b6d4832a22f67262ea612cf2fa44..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cfa9eb31098e12b8ba587017f45372c53a080745eda78fe23c8ca5a6b200bec3 -size 49557504 diff --git a/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperEncoder_float.onnx.zip b/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperEncoder_float.onnx.zip deleted file mode 100644 index 036995e1fd0ed338f5c1399c7a541035c453e5d1..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs8550-proxy/Whisper-Base_HfWhisperEncoder_float.onnx.zip +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d8b94fc400ed3d4df231dfa76ce59d2132db02013554141073cb4f5994ad10ae -size 47020155 diff --git a/precompiled/qualcomm-qcs8550-proxy/tool-versions.yaml b/precompiled/qualcomm-qcs8550-proxy/tool-versions.yaml deleted file mode 100644 index 2651df2a5778b3f91e7ee070551106ab67282c06..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs8550-proxy/tool-versions.yaml +++ /dev/null @@ -1,4 +0,0 @@ -tool_versions: - precompiled_qnn_onnx: - qairt: 2.37.1.250807093845_124904 - onnx_runtime: 1.23.0 diff --git a/precompiled/qualcomm-qcs9075-proxy/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-qcs9075-proxy/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index 22ece87e8c5abb3672960389f1847889a79eeb57..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs9075-proxy/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b674100002ccc5b1561cc3638f07189be4e92437a0b9c0ef3d99dde1af100af2 -size 151851008 diff --git a/precompiled/qualcomm-qcs9075-proxy/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-qcs9075-proxy/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index 75a0b3a35963c34a244018e8f354833d9fd03e6a..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs9075-proxy/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a1fab47565579c2562f7cf1eca63f1af837813fddbea6494715d1d5ba8b69bbd -size 49582080 diff --git a/precompiled/qualcomm-qcs9075-proxy/tool-versions.yaml b/precompiled/qualcomm-qcs9075-proxy/tool-versions.yaml deleted file mode 100644 index 4cb4c03408f55902c17ea51b9b055908dfbcac32..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-qcs9075-proxy/tool-versions.yaml +++ /dev/null @@ -1,3 +0,0 @@ -tool_versions: - qnn_context_binary: - qairt: 2.40.0.251030114326_189385-auto diff --git a/precompiled/qualcomm-sa7255p/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-sa7255p/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index d777308bbc3050e6ae183d892fd01db9f9f1c331..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa7255p/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:acc3f9971e6f17fc359ce48c01d40690bf2b9e9c36ea95faacdb72d6fd1d388d -size 151851008 diff --git a/precompiled/qualcomm-sa7255p/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-sa7255p/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index 8aa5bb89f37efecf645566aee06ca079e5ff911d..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa7255p/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d2d1a746ed398611c5a751a9ec6a2c2263add2ae310250d7f95e8ce8a67dea63 -size 49537024 diff --git a/precompiled/qualcomm-sa7255p/tool-versions.yaml b/precompiled/qualcomm-sa7255p/tool-versions.yaml deleted file mode 100644 index 4cb4c03408f55902c17ea51b9b055908dfbcac32..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa7255p/tool-versions.yaml +++ /dev/null @@ -1,3 +0,0 @@ -tool_versions: - qnn_context_binary: - qairt: 2.40.0.251030114326_189385-auto diff --git a/precompiled/qualcomm-sa8255p-proxy/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-sa8255p-proxy/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index ed6e929585f9ed8a6795dc38b666ccca048b5289..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8255p-proxy/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:48ce8e1ee7f16a0aea384943b7630a623cc3dee61754eeb120b3e1a8c11ee1d8 -size 151846912 diff --git a/precompiled/qualcomm-sa8255p-proxy/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-sa8255p-proxy/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index a38d01fd7207b6fc002ba641f51c3cf6b220f411..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8255p-proxy/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:178eded6614e6d5f8a5c3e0d3f913b8c2d74b1b7e356f8c9f589351fdc225633 -size 49557504 diff --git a/precompiled/qualcomm-sa8255p-proxy/tool-versions.yaml b/precompiled/qualcomm-sa8255p-proxy/tool-versions.yaml deleted file mode 100644 index dd8b2661f081194cd120bbfbfedc0d2de466fa2d..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8255p-proxy/tool-versions.yaml +++ /dev/null @@ -1,3 +0,0 @@ -tool_versions: - qnn_context_binary: - qairt: 2.40.0.251030114326_189385 diff --git a/precompiled/qualcomm-sa8295p/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-sa8295p/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index a81b6be0d703d7b63acaa20a6bf4dc9147c9ce16..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8295p/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2c5790b3ac1b689abc59cc42540498128f37e6e9da6d149fa768a5cbcc069df8 -size 151306240 diff --git a/precompiled/qualcomm-sa8295p/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-sa8295p/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index 858473af668706a8599b5f36f07afce5c39792b8..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8295p/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b32a93e814b4df16c2e61e4ed58a38425fa1d0c06383a60f67e9200321bbe184 -size 48820224 diff --git a/precompiled/qualcomm-sa8295p/tool-versions.yaml b/precompiled/qualcomm-sa8295p/tool-versions.yaml deleted file mode 100644 index 4cb4c03408f55902c17ea51b9b055908dfbcac32..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8295p/tool-versions.yaml +++ /dev/null @@ -1,3 +0,0 @@ -tool_versions: - qnn_context_binary: - qairt: 2.40.0.251030114326_189385-auto diff --git a/precompiled/qualcomm-sa8650p-proxy/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-sa8650p-proxy/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index ed6e929585f9ed8a6795dc38b666ccca048b5289..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8650p-proxy/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:48ce8e1ee7f16a0aea384943b7630a623cc3dee61754eeb120b3e1a8c11ee1d8 -size 151846912 diff --git a/precompiled/qualcomm-sa8650p-proxy/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-sa8650p-proxy/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index 08d84de1f46c6b77eb5ac94a7aad11c41d4fc868..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8650p-proxy/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:268c206382e633ce4a352f2926058308a28a892cf9eb66a8cf1ae01499911814 -size 49557504 diff --git a/precompiled/qualcomm-sa8650p-proxy/tool-versions.yaml b/precompiled/qualcomm-sa8650p-proxy/tool-versions.yaml deleted file mode 100644 index dd8b2661f081194cd120bbfbfedc0d2de466fa2d..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8650p-proxy/tool-versions.yaml +++ /dev/null @@ -1,3 +0,0 @@ -tool_versions: - qnn_context_binary: - qairt: 2.40.0.251030114326_189385 diff --git a/precompiled/qualcomm-sa8775p/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-sa8775p/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index 22ece87e8c5abb3672960389f1847889a79eeb57..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8775p/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b674100002ccc5b1561cc3638f07189be4e92437a0b9c0ef3d99dde1af100af2 -size 151851008 diff --git a/precompiled/qualcomm-sa8775p/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-sa8775p/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index 75a0b3a35963c34a244018e8f354833d9fd03e6a..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8775p/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a1fab47565579c2562f7cf1eca63f1af837813fddbea6494715d1d5ba8b69bbd -size 49582080 diff --git a/precompiled/qualcomm-sa8775p/tool-versions.yaml b/precompiled/qualcomm-sa8775p/tool-versions.yaml deleted file mode 100644 index 4cb4c03408f55902c17ea51b9b055908dfbcac32..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-sa8775p/tool-versions.yaml +++ /dev/null @@ -1,3 +0,0 @@ -tool_versions: - qnn_context_binary: - qairt: 2.40.0.251030114326_189385-auto diff --git a/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index c714ded6a533838895f7ebe3e4bbb7d8689fda8d..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e71c11b6c3c005db8a3ac12cf48854312e3d3355cc4a54f2aa0fcfc59d2216e0 -size 151826432 diff --git a/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperDecoder_float.onnx.zip b/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperDecoder_float.onnx.zip deleted file mode 100644 index e3ece45b09602e2c59134397b5842c96ea3d39f2..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperDecoder_float.onnx.zip +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d08df5b26324dc9eb356e390cf07d5ec78a28d778d50a0994aa72d3c25e85a1e -size 137226158 diff --git a/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index 9b1f938d1898e8f62fb7384ffae016900c4c710d..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f5aa8e805b3154bbd77585c5238f4fdb3e868a12497971e24450a2242a4abeb7 -size 49598464 diff --git a/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperEncoder_float.onnx.zip b/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperEncoder_float.onnx.zip deleted file mode 100644 index 5f765b402c83f1fa00c9c1e81b5511ed805b118b..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Base_HfWhisperEncoder_float.onnx.zip +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e63ca2cf524e9746185487aa1be513fc21d573b3a5f169392a19ea7b7b516ae5 -size 46951725 diff --git a/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/tool-versions.yaml b/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/tool-versions.yaml deleted file mode 100644 index 2651df2a5778b3f91e7ee070551106ab67282c06..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8-elite-for-galaxy/tool-versions.yaml +++ /dev/null @@ -1,4 +0,0 @@ -tool_versions: - precompiled_qnn_onnx: - qairt: 2.37.1.250807093845_124904 - onnx_runtime: 1.23.0 diff --git a/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index e34529345ea04bd5bb2e9cd04c022ee567748a39..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fbcd13d1891e20100566890cd231a0530f86e422f77870f3759d85eb94474bf8 -size 152006656 diff --git a/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperDecoder_float.onnx.zip b/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperDecoder_float.onnx.zip deleted file mode 100644 index 9665859d7ddfb81ea38763551643c56c030f6187..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperDecoder_float.onnx.zip +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4a66bd15c490c9455142d42b4ac71573cd81ed9974231efb6ce98d0c1a552220 -size 137271892 diff --git a/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index bb7abf80b128ee3387c53456709f2ed9c4913137..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:625e174a128999c4d59c1fbbba996f2df9fd52373af670255fb25bcd46a4bdaa -size 49840128 diff --git a/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperEncoder_float.onnx.zip b/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperEncoder_float.onnx.zip deleted file mode 100644 index af7d3bddf5fc144caa1d925c4db25279d89401e9..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Base_HfWhisperEncoder_float.onnx.zip +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e88a62c85f7ed1f8c411205552364fa95f020c59e5cb15ea6c707a7a60d5e691 -size 46981264 diff --git a/precompiled/qualcomm-snapdragon-8-elite-gen5/tool-versions.yaml b/precompiled/qualcomm-snapdragon-8-elite-gen5/tool-versions.yaml deleted file mode 100644 index 2651df2a5778b3f91e7ee070551106ab67282c06..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8-elite-gen5/tool-versions.yaml +++ /dev/null @@ -1,4 +0,0 @@ -tool_versions: - precompiled_qnn_onnx: - qairt: 2.37.1.250807093845_124904 - onnx_runtime: 1.23.0 diff --git a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index b8a3d49a38a54d25120da848037638f0d42901ef..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7940d597aea934e2b048454b358de2bbbeba406bb3ed0dc920ae90586da8e326 -size 151851008 diff --git a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperDecoder_float.onnx.zip b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperDecoder_float.onnx.zip deleted file mode 100644 index 1a186323236421ae8252b0999c6b72068a35aab9..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperDecoder_float.onnx.zip +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:69ed69616e6ecf77a86282dcbdfc06ba0408790fa17d4b0aff442e182bb263b0 -size 137235711 diff --git a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index 8d9855c9cfcb190f8401216795d8b692ef03e3be..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7b01b69517a8d7c61b7559648ce7754becafb587ebfa40e7db9c8a5d74b904bc -size 49569792 diff --git a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperEncoder_float.onnx.zip b/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperEncoder_float.onnx.zip deleted file mode 100644 index 040c9fd738b9439095fcb6cfa5357731c61f6343..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8gen3/Whisper-Base_HfWhisperEncoder_float.onnx.zip +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:63d17a5744d766999147e745eae02b5c2e71520dfbb448020c6d05518ddab7c8 -size 47041448 diff --git a/precompiled/qualcomm-snapdragon-8gen3/tool-versions.yaml b/precompiled/qualcomm-snapdragon-8gen3/tool-versions.yaml deleted file mode 100644 index 2651df2a5778b3f91e7ee070551106ab67282c06..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-8gen3/tool-versions.yaml +++ /dev/null @@ -1,4 +0,0 @@ -tool_versions: - precompiled_qnn_onnx: - qairt: 2.37.1.250807093845_124904 - onnx_runtime: 1.23.0 diff --git a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperDecoder_float.bin b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperDecoder_float.bin deleted file mode 100644 index 57badd551a216cdba52c6e1f4e7d794d94a8f366..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperDecoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9ef2258ddaf516621f25715a9911d6c145f11fdabc9adaea329d66ed62d85d44 -size 151846912 diff --git a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperDecoder_float.onnx.zip b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperDecoder_float.onnx.zip deleted file mode 100644 index c07dd6e14347f32069c575d3c3ceedef0e624e5c..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperDecoder_float.onnx.zip +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:03367d21d01ab08fbd5da820f1193f4009e436877eb5521b561308ac1e278271 -size 137232338 diff --git a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperEncoder_float.bin b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperEncoder_float.bin deleted file mode 100644 index dd166f005210d1bc5239009639d4604cd528a29c..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperEncoder_float.bin +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8f42c330b0144990601e321dc0b2a789f277edfefbf3dcbf48ac39aecd1c6bff -size 49557504 diff --git a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperEncoder_float.onnx.zip b/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperEncoder_float.onnx.zip deleted file mode 100644 index 582fa2ddcf06c268730f04887918bba5aca8b248..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-x-elite/Whisper-Base_HfWhisperEncoder_float.onnx.zip +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:08a028dd1f585f9394c2e15238378361a75521294197ddebccce9cb598d20f1c -size 47012866 diff --git a/precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml b/precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml deleted file mode 100644 index 2651df2a5778b3f91e7ee070551106ab67282c06..0000000000000000000000000000000000000000 --- a/precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml +++ /dev/null @@ -1,4 +0,0 @@ -tool_versions: - precompiled_qnn_onnx: - qairt: 2.37.1.250807093845_124904 - onnx_runtime: 1.23.0