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.

Deploying Whisper-Medium on-device

This model is compatible with the Qualcomm Voice AI SDK. Download the SDK from the Qualcomm Package Manager to deploy this model on-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 For Galaxy Mobile QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50, ONNX Runtime 1.27.1 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50, ONNX Runtime 1.27.1 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® X2 Elite QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® X Elite QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8775P QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA7255P QAIRT 2.50 Download
QNN_CONTEXT_BINARY float Qualcomm® SA8295P QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® X2 Elite QAIRT 2.50 Download
VOICE_AI float Snapdragon® X Elite QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA8775P QAIRT 2.50 Download
VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA7255P QAIRT 2.50 Download
VOICE_AI float Qualcomm® SA8295P QAIRT 2.50 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:

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

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 For Galaxy Mobile 25.645 ms 154 - 167 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 24.24 ms 109 - 121 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 17.598 ms 159 - 159 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 30.185 ms 725 - 725 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 30.398 ms 200 - 210 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 40.376 ms 160 - 323 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 33.339 ms 159 - 162 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 36.984 ms 159 - 322 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 30.185 ms 725 - 725 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 24.24 ms 109 - 121 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 21.855 ms 140 - 155 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 23.407 ms 63 - 73 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 18.671 ms 160 - 160 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 29.887 ms 160 - 160 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 29.779 ms 131 - 140 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 37.858 ms 160 - 177 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 41.552 ms 160 - 341 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 33.711 ms 158 - 161 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 36.697 ms 160 - 172 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 36.697 ms 160 - 172 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 37.858 ms 160 - 177 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 37.182 ms 160 - 340 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 29.887 ms 160 - 160 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 23.407 ms 63 - 73 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 39.72 ms 113 - 119 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 21.826 ms 110 - 121 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 23.55 ms 49 - 58 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 18.646 ms 160 - 160 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 29.147 ms 160 - 160 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 28.491 ms 158 - 172 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 41.457 ms 160 - 341 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 34.27 ms 158 - 161 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 36.842 ms 146 - 158 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 36.842 ms 146 - 158 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 37.155 ms 160 - 340 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 29.147 ms 160 - 160 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 23.55 ms 49 - 58 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 39.48 ms 91 - 97 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 137.038 ms 302 - 314 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 178.552 ms 304 - 316 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 140.834 ms 528 - 528 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 331.865 ms 697 - 697 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 238.579 ms 303 - 315 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 420.347 ms 249 - 253 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 327.167 ms 0 - 770 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 395.03 ms 302 - 306 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 331.865 ms 697 - 697 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 178.552 ms 304 - 316 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 133.882 ms 25 - 34 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 173.976 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 140.924 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 329.761 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 237.612 ms 2 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 506.575 ms 0 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 418.357 ms 0 - 145 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 324.462 ms 5 - 29 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8650P 441.603 ms 1 - 12 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8255P 441.603 ms 1 - 12 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® QCS8450 506.575 ms 0 - 10 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 393.772 ms 0 - 144 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 329.761 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 173.976 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 439.28 ms 1 - 7 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 134.355 ms 1 - 13 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 175.536 ms 1 - 15 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 141.655 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 329.046 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 235.018 ms 1 - 14 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 419.531 ms 0 - 145 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 326.391 ms 25 - 28 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 441.333 ms 1 - 12 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 441.333 ms 1 - 12 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 395.018 ms 0 - 144 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 329.046 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 175.536 ms 1 - 15 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 439.794 ms 1 - 7 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