Hugging Face's logo

qualcomm
/
OpusMT-Fr-En

Text Generation
PyTorch
foundation
android
Model card Files
xet
 Community

OpusMT-Fr-En: Optimized for Qualcomm Devices

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

This is based on the implementation of OpusMT-Fr-En 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-Fr-En 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-Fr-En 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-Fr-En 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 (French text)
  • Max input sequence length: 256 tokens
  • Max output sequence length: 256 tokens
  • Model checkpoint: Helsinki-NLP/opus-mt-fr-en
  • 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 1 - 10 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 1.407 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 1.31 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 2.06 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 2.883 ms 3 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 2.96 ms 12 - 27 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.269 ms 2 - 3 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 2.931 ms 13 - 18 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 2.931 ms 13 - 18 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 2.931 ms 13 - 18 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 2.883 ms 3 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 2.775 ms 12 - 27 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 2.06 ms 12 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 1.407 ms 0 - 9 MB NPU
decoder VOICE_AI float Qualcomm® SA7255P 3.905 ms 11 - 20 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 3.121 ms 10 - 15 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Extreme Gen 6 Mobile 1.291 ms 1 - 10 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 6 Mobile 1.253 ms 1 - 11 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.927 ms 0 - 8 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.964 ms 0 - 8 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X2 Elite 0.901 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X Elite 1.43 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Gen 1 Mobile 1.656 ms 1 - 10 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 1.861 ms 0 - 5 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.458 ms 0 - 2 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8775P 1.917 ms 2 - 11 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8650P 1.917 ms 2 - 11 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8255P 1.917 ms 2 - 11 MB NPU
decoder VOICE_AI w8a16 Qualcomm® QCS8450 1.656 ms 1 - 10 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 1.8 ms 4 - 7 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.43 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 0.964 ms 0 - 8 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA7255P 2.746 ms 0 - 8 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8295P 2.123 ms 1 - 6 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.894 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 2.608 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 2.947 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 2.552 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 4.885 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 6.166 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 5.157 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.905 ms 0 - 1 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 5.239 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 5.239 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 5.239 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 6.166 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 5.09 ms 2 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 4.885 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 2.947 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® SA7255P 8.37 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 6.362 ms 0 - 5 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Extreme Gen 6 Mobile 1.138 ms 0 - 9 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 6 Mobile 2.44 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.395 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.794 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X2 Elite 2.305 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X Elite 4.631 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Gen 1 Mobile 5.54 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 4.601 ms 0 - 4 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.637 ms 0 - 4 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8775P 4.752 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8650P 4.752 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8255P 4.752 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® QCS8450 5.54 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 4.548 ms 0 - 4 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 4.631 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 2.794 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA7255P 7.846 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8295P 6.011 ms 0 - 5 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.93 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 6 Mobile 2.266 ms 0 - 10 MB NPU

License

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