Hugging Face's logo

qualcomm
/
OpusMT-En-De

Text Generation
PyTorch
foundation
android
Model card Files
xet
 Community

OpusMT-En-De: Optimized for Qualcomm Devices

OpusMT English to German translation model is a state-of-the-art neural machine translation system designed for translating English text into German. This model is based on the Marian transformer architecture and has been optimized for edge inference by splitting into encoder and decoder components with modified attention mechanisms. It exhibits robust performance for real-world translation tasks, making it highly reliable for practical applications. The model supports input sequences up to 256 tokens and can generate German translations with high accuracy.

This is based on the implementation of OpusMT-En-De 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 OpusMT-En-De 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
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 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
VOICE_AI float Snapdragon® 8 Elite Extreme Gen 6 Mobile QAIRT 2.50 Download
VOICE_AI float Snapdragon® 8 Elite Gen 6 Mobile QAIRT 2.50 Download
VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile QAIRT 2.50 Download
VOICE_AI w8a16 Snapdragon® X2 Elite QAIRT 2.50 Download
VOICE_AI w8a16 Snapdragon® X Elite QAIRT 2.50 Download
VOICE_AI w8a16 Snapdragon® 8 Gen 1 Mobile QAIRT 2.50 Download
VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 QAIRT 2.50 Download
VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) QAIRT 2.50 Download
VOICE_AI w8a16 Qualcomm® SA8775P QAIRT 2.50 Download
VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 QAIRT 2.50 Download
VOICE_AI w8a16 Qualcomm® SA7255P QAIRT 2.50 Download
VOICE_AI w8a16 Qualcomm® SA8295P QAIRT 2.50 Download
VOICE_AI w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile QAIRT 2.50 Download
VOICE_AI w8a16 Snapdragon® 8 Elite Gen 6 Mobile QAIRT 2.50 Download

For more device-specific assets and performance metrics, visit OpusMT-En-De 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 OpusMT-En-De on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

  • Attention heads: 8
  • Hidden dimension: 512
  • Input resolution: 256 tokens (English text)
  • Max input sequence length: 256 tokens
  • Max output sequence length: 256 tokens
  • Model checkpoint: Helsinki-NLP/opus-mt-en-de
  • Model size (decoder) (float): 340 MB
  • Model size (decoder) (w8a16): 90.8 MB
  • Model size (encoder) (float): 212 MB
  • Model size (encoder) (w8a16): 55.2 MB
  • Number of decoder layers: 6
  • Number of encoder layers: 6
  • Number of parameters (decoder): 55.7M
  • Number of parameters (encoder): 55.5M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
decoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.309 ms 0 - 8 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 1.474 ms 0 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 1.255 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 2.073 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 2.828 ms 2 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 2.954 ms 12 - 27 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.273 ms 2 - 4 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 2.893 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 2.893 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 2.893 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 2.828 ms 2 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 2.749 ms 14 - 28 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 2.073 ms 12 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 1.474 ms 0 - 12 MB NPU
decoder VOICE_AI float Qualcomm® SA7255P 3.897 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 3.07 ms 10 - 16 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Extreme Gen 6 Mobile 1.232 ms 1 - 10 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 6 Mobile 1.289 ms 1 - 11 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.912 ms 1 - 8 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.961 ms 0 - 8 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X2 Elite 0.899 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X Elite 1.434 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Gen 1 Mobile 1.637 ms 0 - 9 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 1.827 ms 0 - 5 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.457 ms 0 - 2 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8775P 1.893 ms 2 - 11 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8650P 1.893 ms 2 - 11 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8255P 1.893 ms 2 - 11 MB NPU
decoder VOICE_AI w8a16 Qualcomm® QCS8450 1.637 ms 0 - 9 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 1.75 ms 2 - 5 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.434 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 0.961 ms 0 - 8 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA7255P 2.732 ms 0 - 8 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8295P 2.087 ms 1 - 6 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.892 ms 0 - 10 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 6 Mobile 0.875 ms 0 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.598 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 3.04 ms 0 - 12 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 2.599 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 4.915 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 6.086 ms 1 - 11 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 5.108 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.99 ms 0 - 2 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 5.242 ms 0 - 5 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 5.242 ms 0 - 5 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 5.242 ms 0 - 5 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 6.086 ms 1 - 11 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 5.122 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 4.915 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 3.04 ms 0 - 12 MB NPU
encoder VOICE_AI float Qualcomm® SA7255P 8.39 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 6.405 ms 0 - 5 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Extreme Gen 6 Mobile 1.127 ms 0 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 6 Mobile 2.426 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.399 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.8 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X2 Elite 2.261 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X Elite 4.598 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Gen 1 Mobile 5.489 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 4.63 ms 0 - 4 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.631 ms 0 - 1 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8775P 4.729 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8650P 4.729 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8255P 4.729 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® QCS8450 5.489 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 4.538 ms 0 - 4 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 4.598 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 2.8 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA7255P 7.863 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8295P 6.016 ms 0 - 5 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.924 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 6 Mobile 2.245 ms 0 - 9 MB NPU

License

  • The license for the original implementation of OpusMT-En-De can be found here.

References

Community

Downloads last month

-

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