Hugging Face's logo

qualcomm
/
Whisper-Medium

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community

Whisper-Medium: Optimized for Qualcomm Devices

HuggingFace Whisper-Medium 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-Medium found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up 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

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.42, ONNX Runtime 1.24.3 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 QAIRT 2.42, ONNX Runtime 1.24.3 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® X2 Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® X Elite QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8775P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA7255P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8295P QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® QCS9075 QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit Whisper-Medium on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models 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 option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for Whisper-Medium on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.speech_recognition

Model Stats:

  • Model checkpoint: openai/whisper-medium
  • Input resolution: 80x3000 (30 seconds audio)
  • Max decoded sequence length: 200 tokens
  • Number of parameters (encoder): 384M
  • Model size (encoder) (float): 1.54GB
  • Number of parameters (decoder): 385M
  • Model size (decoder) (float): 1.54GB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 20.697 ms 165 - 174 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 24.281 ms 88 - 98 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 16.698 ms 728 - 728 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 29.259 ms 725 - 725 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 29.259 ms 725 - 725 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 30.118 ms 200 - 212 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 34.215 ms 160 - 162 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 36.483 ms 160 - 322 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 24.281 ms 88 - 98 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 20.793 ms 160 - 171 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 23.602 ms 103 - 112 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 18.761 ms 160 - 160 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 27.217 ms 160 - 160 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 27.217 ms 160 - 160 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 28.437 ms 160 - 173 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 51.654 ms 149 - 159 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 34.279 ms 135 - 137 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 36.732 ms 146 - 155 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 36.732 ms 146 - 155 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 36.732 ms 146 - 155 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 37.005 ms 160 - 339 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 59.013 ms 158 - 173 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 51.654 ms 149 - 159 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 38.279 ms 109 - 115 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 23.602 ms 103 - 112 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 148.913 ms 302 - 313 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 187.258 ms 304 - 316 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 216.189 ms 700 - 700 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 333.907 ms 699 - 699 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 333.907 ms 699 - 699 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 249.196 ms 303 - 315 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 332.159 ms 298 - 300 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 406.547 ms 301 - 304 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 187.258 ms 304 - 316 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 151.181 ms 9 - 17 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 219.615 ms 1 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 152.885 ms 1 - 1 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 364.541 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 364.541 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 274.424 ms 3 - 14 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 (Proxy) 1339.386 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 360.853 ms 0 - 138 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 441.412 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 441.412 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8775P 441.412 ms 0 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 438.55 ms 0 - 143 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 (Proxy) 755.468 ms 1 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 1339.386 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 508.432 ms 1 - 7 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 219.615 ms 1 - 13 MB NPU

License

  • The license for the original implementation of Whisper-Medium can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Automatic Speech Recognition
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support