You can deploy this model and start earning money today!

qualcomm/
Whisper-Medium

Name: Whisper-Medium
Availability: InStock

pytorch

foundation

android

automatic-speech-recognition

apache-2.0

Views

No views yet

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® X2 Elite	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 1 Mobile	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-8275	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45, ONNX Runtime 1.27.1	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® Dragonwing™ IQ-8275	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-9075	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	Snapdragon® 8 Elite Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45	Download
VOICE_AI	float	Snapdragon® X2 Elite	QAIRT 2.45	Download
VOICE_AI	float	Snapdragon® X Elite	QAIRT 2.45	Download
VOICE_AI	float	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.45	Download
VOICE_AI	float	Snapdragon® 8 Gen 1 Mobile	QAIRT 2.45	Download
VOICE_AI	float	Qualcomm® Dragonwing™ IQ-8275	QAIRT 2.45	Download
VOICE_AI	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	QAIRT 2.45	Download
VOICE_AI	float	Qualcomm® SA8775P	QAIRT 2.45	Download
VOICE_AI	float	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.45	Download
VOICE_AI	float	Qualcomm® SA7255P	QAIRT 2.45	Download
VOICE_AI	float	Qualcomm® SA8295P	QAIRT 2.45	Download
VOICE_AI	float	Snapdragon® 8 Elite Mobile	QAIRT 2.45	Download
VOICE_AI	float	Snapdragon® 8 Elite Gen 5 Mobile	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:

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® X2 Elite	17.63 ms	160 - 160 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	27.213 ms	726 - 726 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	29.455 ms	199 - 209 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 1 Mobile	58.436 ms	199 - 214 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-8275	39.706 ms	160 - 323 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	34.785 ms	146 - 148 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS8450	58.436 ms	199 - 214 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-9075	37.699 ms	159 - 322 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	27.213 ms	726 - 726 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ Q-8750	24.352 ms	50 - 61 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	24.352 ms	50 - 61 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	21.462 ms	153 - 164 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	18.97 ms	160 - 160 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	27.533 ms	160 - 160 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	28.835 ms	134 - 143 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-8275	39.416 ms	160 - 340 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-8275	51.657 ms	144 - 155 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	33.723 ms	121 - 141 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	36.697 ms	160 - 172 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® Dragonwing™ IQ-9075	37.0 ms	160 - 340 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-X7181	27.533 ms	160 - 160 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ Q-8750	23.6 ms	84 - 98 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	51.657 ms	144 - 155 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA8295P	38.566 ms	109 - 115 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	23.6 ms	84 - 98 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	21.24 ms	158 - 173 MB	NPU
decoder	VOICE_AI	float	Snapdragon® X2 Elite	18.785 ms	160 - 160 MB	NPU
decoder	VOICE_AI	float	Snapdragon® X Elite	27.354 ms	160 - 160 MB	NPU
decoder	VOICE_AI	float	Snapdragon® 8 Gen 3 Mobile	28.295 ms	135 - 143 MB	NPU
decoder	VOICE_AI	float	Qualcomm® Dragonwing™ IQ-8275	39.434 ms	160 - 340 MB	NPU
decoder	VOICE_AI	float	Qualcomm® Dragonwing™ IQ-8275	51.806 ms	147 - 158 MB	NPU
decoder	VOICE_AI	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	33.318 ms	136 - 138 MB	NPU
decoder	VOICE_AI	float	Qualcomm® SA8775P	36.842 ms	146 - 158 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	36.538 ms	160 - 340 MB	NPU
decoder	VOICE_AI	float	Qualcomm® Dragonwing™ IQ-X7181	27.354 ms	160 - 160 MB	NPU
decoder	VOICE_AI	float	Qualcomm® Dragonwing™ Q-8750	23.51 ms	89 - 103 MB	NPU
decoder	VOICE_AI	float	Qualcomm® SA7255P	51.806 ms	147 - 158 MB	NPU
decoder	VOICE_AI	float	Qualcomm® SA8295P	37.873 ms	112 - 118 MB	NPU
decoder	VOICE_AI	float	Snapdragon® 8 Elite Mobile	23.51 ms	89 - 103 MB	NPU
decoder	VOICE_AI	float	Snapdragon® 8 Elite Gen 5 Mobile	21.027 ms	86 - 97 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	153.518 ms	529 - 529 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	366.093 ms	698 - 698 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	275.915 ms	306 - 318 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 1 Mobile	773.288 ms	282 - 296 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-8275	471.111 ms	159 - 163 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	365.614 ms	0 - 770 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS8450	773.288 ms	282 - 296 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-9075	441.006 ms	161 - 165 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	366.093 ms	698 - 698 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ Q-8750	233.801 ms	305 - 317 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	233.801 ms	305 - 317 MB	NPU
encoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	156.611 ms	302 - 313 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	153.148 ms	0 - 0 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	364.918 ms	0 - 0 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	276.544 ms	61 - 69 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-8275	471.127 ms	0 - 144 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-8275	1339.536 ms	1 - 11 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	362.368 ms	0 - 135 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	441.603 ms	1 - 12 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® Dragonwing™ IQ-9075	437.179 ms	0 - 143 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-X7181	364.918 ms	0 - 0 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ Q-8750	220.298 ms	1 - 14 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	1339.536 ms	1 - 11 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA8295P	508.791 ms	1 - 6 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	220.298 ms	1 - 14 MB	NPU
encoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	151.752 ms	25 - 34 MB	NPU
encoder	VOICE_AI	float	Snapdragon® X2 Elite	154.199 ms	0 - 0 MB	NPU
encoder	VOICE_AI	float	Snapdragon® X Elite	365.046 ms	0 - 0 MB	NPU
encoder	VOICE_AI	float	Snapdragon® 8 Gen 3 Mobile	275.659 ms	1 - 8 MB	NPU
encoder	VOICE_AI	float	Qualcomm® Dragonwing™ IQ-8275	471.328 ms	0 - 144 MB	NPU
encoder	VOICE_AI	float	Qualcomm® Dragonwing™ IQ-8275	1340.474 ms	1 - 11 MB	NPU
encoder	VOICE_AI	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	363.144 ms	0 - 2 MB	NPU
encoder	VOICE_AI	float	Qualcomm® SA8775P	441.333 ms	1 - 12 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	506.869 ms	0 - 143 MB	NPU
encoder	VOICE_AI	float	Qualcomm® Dragonwing™ IQ-X7181	365.046 ms	0 - 0 MB	NPU
encoder	VOICE_AI	float	Qualcomm® Dragonwing™ Q-8750	220.789 ms	1 - 13 MB	NPU
encoder	VOICE_AI	float	Qualcomm® SA7255P	1340.474 ms	1 - 11 MB	NPU
encoder	VOICE_AI	float	Qualcomm® SA8295P	509.071 ms	1 - 6 MB	NPU
encoder	VOICE_AI	float	Snapdragon® 8 Elite Mobile	220.789 ms	1 - 13 MB	NPU
encoder	VOICE_AI	float	Snapdragon® 8 Elite Gen 5 Mobile	149.542 ms	1 - 14 MB	NPU

License

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

References

Community

Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
For questions or feedback please reach out to us.

qualcomm/Whisper-Medium