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 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® X Elite QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile QAIRT 2.50, ONNX Runtime 1.30.0 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 1.30.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50, ONNX Runtime 1.30.0 Download
PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50, ONNX Runtime 1.30.0 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 22.395 ms 154 - 166 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 23.981 ms 102 - 114 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 17.952 ms 160 - 160 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 30.348 ms 726 - 726 MB NPU
decoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 29.937 ms 200 - 211 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 40.601 ms 159 - 323 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 35.304 ms 0 - 733 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 37.439 ms 159 - 322 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 30.348 ms 726 - 726 MB NPU
decoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 23.981 ms 102 - 114 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 20.824 ms 91 - 100 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 23.471 ms 49 - 58 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 18.343 ms 160 - 160 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 28.577 ms 160 - 160 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 28.947 ms 158 - 172 MB NPU
decoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 37.619 ms 160 - 178 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 41.422 ms 160 - 341 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 33.419 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 37.619 ms 160 - 178 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 37.294 ms 160 - 340 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 28.577 ms 160 - 160 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 23.471 ms 49 - 58 MB NPU
decoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 39.621 ms 102 - 109 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 21.558 ms 110 - 120 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 23.313 ms 136 - 151 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 18.903 ms 160 - 160 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 29.05 ms 160 - 160 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 28.764 ms 158 - 172 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 39.943 ms 160 - 341 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 34.89 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 37.28 ms 160 - 340 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 29.05 ms 160 - 160 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 23.313 ms 136 - 151 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 38.953 ms 102 - 109 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 139.59 ms 306 - 318 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Elite For Galaxy Mobile 178.532 ms 305 - 316 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X2 Elite 176.939 ms 528 - 528 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® X Elite 331.024 ms 698 - 698 MB NPU
encoder PRECOMPILED_QNN_ONNX float Snapdragon® 8 Gen 3 Mobile 245.213 ms 304 - 317 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-8275 420.22 ms 257 - 262 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 327.634 ms 0 - 770 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-9075 394.769 ms 305 - 309 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ IQ-X7181 331.024 ms 698 - 698 MB NPU
encoder PRECOMPILED_QNN_ONNX float Qualcomm® Dragonwing™ Q-8750 178.532 ms 305 - 316 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 135.28 ms 1 - 13 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Elite For Galaxy Mobile 173.075 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X2 Elite 140.564 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® X Elite 332.026 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 3 Mobile 235.923 ms 29 - 37 MB NPU
encoder QNN_CONTEXT_BINARY float Snapdragon® 8 Gen 1 Mobile 513.256 ms 0 - 14 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-8275 419.799 ms 0 - 145 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ QCS8550 (Proxy) 328.591 ms 0 - 3 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 513.256 ms 0 - 14 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-9075 393.678 ms 2 - 146 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ IQ-X7181 332.026 ms 0 - 0 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® Dragonwing™ Q-8750 173.075 ms 1 - 9 MB NPU
encoder QNN_CONTEXT_BINARY float Qualcomm® SA8295P 440.09 ms 1 - 7 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 137.041 ms 25 - 34 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 172.082 ms 0 - 13 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 141.439 ms 1 - 1 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 332.399 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 238.448 ms 1 - 8 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 418.423 ms 0 - 145 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 323.473 ms 1 - 3 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 394.754 ms 0 - 144 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 332.399 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 172.082 ms 0 - 13 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 440.682 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