Hugging Face's logo

qualcomm
/
OpusMT-En-Fr

Text Generation
PyTorch
foundation
android
Model card Files
xet
 Community

OpusMT-En-Fr: Optimized for Qualcomm Devices

OpusMT English to French translation model is a state-of-the-art neural machine translation system designed for translating English text into French. 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 French translations with high accuracy.

This is based on the implementation of OpusMT-En-Fr 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-Fr 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-Fr 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-Fr 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-fr
  • 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 1.321 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 1.467 ms 0 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 1.317 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 2.139 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 2.874 ms 3 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 2.977 ms 12 - 27 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.301 ms 2 - 3 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 2.926 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 2.926 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 2.926 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 2.874 ms 3 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 2.789 ms 12 - 27 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 2.139 ms 12 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 1.467 ms 0 - 12 MB NPU
decoder VOICE_AI float Qualcomm® SA7255P 3.91 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 3.058 ms 10 - 15 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Extreme Gen 6 Mobile 1.35 ms 1 - 11 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 6 Mobile 1.37 ms 1 - 11 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.922 ms 0 - 8 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.961 ms 0 - 12 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X2 Elite 0.897 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X Elite 1.431 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Gen 1 Mobile 1.655 ms 0 - 10 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 1.865 ms 2 - 6 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.468 ms 0 - 2 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8775P 1.913 ms 3 - 11 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8650P 1.913 ms 3 - 11 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8255P 1.913 ms 3 - 11 MB NPU
decoder VOICE_AI w8a16 Qualcomm® QCS8450 1.655 ms 0 - 10 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 1.765 ms 2 - 5 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.431 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 0.961 ms 0 - 12 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA7255P 2.777 ms 0 - 8 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8295P 2.134 ms 3 - 8 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.895 ms 0 - 10 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 6 Mobile 0.88 ms 0 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.605 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 3.007 ms 0 - 12 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 2.541 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 4.938 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 6.138 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 5.122 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.928 ms 0 - 2 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 5.261 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 5.261 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 5.261 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 6.138 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 5.06 ms 2 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 4.938 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 3.007 ms 0 - 12 MB NPU
encoder VOICE_AI float Qualcomm® SA7255P 8.348 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 6.41 ms 0 - 5 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Extreme Gen 6 Mobile 1.145 ms 0 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 6 Mobile 2.478 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.39 ms 0 - 7 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.79 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X2 Elite 2.307 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X Elite 4.676 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Gen 1 Mobile 5.526 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 4.611 ms 0 - 4 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.633 ms 0 - 1 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8775P 4.765 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8650P 4.765 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8255P 4.765 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® QCS8450 5.526 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 4.539 ms 0 - 4 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 4.676 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 2.79 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA7255P 7.788 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8295P 6.012 ms 0 - 5 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.923 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 6 Mobile 2.223 ms 0 - 10 MB NPU

License

  • The license for the original implementation of OpusMT-En-Fr 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