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® X2 Elite QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile QAIRT 2.45, ONNX Runtime 1.25.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 QAIRT 2.45, ONNX Runtime 1.25.0 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 Snapdragon® 8 Gen 1 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 Mobile QAIRT 2.45 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 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

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® X2 Elite 18.215 ms 159 - 159 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 27.332 ms 726 - 726 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 29.478 ms 201 - 214 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 60.973 ms 199 - 214 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 34.781 ms 0 - 732 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 60.973 ms 199 - 214 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 25.185 ms 154 - 166 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 37.364 ms 159 - 322 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 24.161 ms 121 - 134 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8750 24.161 ms 121 - 134 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS7181 27.332 ms 726 - 726 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 18.543 ms 160 - 160 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 28.141 ms 160 - 160 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 28.753 ms 158 - 172 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 51.545 ms 157 - 166 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 33.949 ms 159 - 162 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 20.729 ms 118 - 128 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 51.545 ms 157 - 166 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 37.37 ms 160 - 340 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 23.488 ms 105 - 119 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 38.394 ms 152 - 163 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8750 23.488 ms 105 - 119 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS7181 28.141 ms 160 - 160 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 153.301 ms 529 - 529 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 364.858 ms 698 - 698 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 279.95 ms 301 - 312 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile 765.713 ms 213 - 226 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8550 (Proxy) 365.081 ms 298 - 300 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8450 765.713 ms 213 - 226 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 Mobile 151.258 ms 290 - 301 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS9075 440.102 ms 165 - 168 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Mobile 233.43 ms 305 - 317 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS8750 233.43 ms 305 - 317 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® QCS7181 364.858 ms 698 - 698 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 154.371 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 366.294 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 274.085 ms 1 - 14 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8275 1339.834 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8550 (Proxy) 363.019 ms 0 - 2 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 Mobile 149.77 ms 1 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA7255P 1339.834 ms 0 - 8 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS9075 438.082 ms 0 - 143 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Mobile 218.424 ms 1 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 507.999 ms 3 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8750 218.424 ms 1 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS7181 366.294 ms 0 - 0 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