Hugging Face's logo

qualcomm
/
OpusMT-Zh-En

Text Generation
PyTorch
foundation
android
Model card Files
xet
 Community

OpusMT-Zh-En: Optimized for Qualcomm Devices

OpusMT Chinese to English translation model is a state-of-the-art neural machine translation system designed for translating Chinese 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-Zh-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-Zh-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 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 OpusMT-Zh-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-Zh-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 (Chinese text)
  • Max input sequence length: 256 tokens
  • Max output sequence length: 256 tokens
  • Model checkpoint: Helsinki-NLP/opus-mt-zh-en
  • Model size (decoder) (float): ~280 MB
  • Model size (encoder) (float): ~280 MB
  • Number of decoder layers: 6
  • Number of encoder layers: 6
  • Number of parameters (decoder): ~74M
  • Number of parameters (encoder): ~74M

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 2.366 ms 0 - 9 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 2.527 ms 0 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 2.462 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 3.339 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 2.733 ms 12 - 19 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 4.037 ms 2 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 4.479 ms 12 - 27 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.421 ms 1 - 3 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 4.266 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 4.266 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 4.037 ms 2 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 4.001 ms 14 - 28 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 3.339 ms 12 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 2.527 ms 0 - 12 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 4.312 ms 12 - 17 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.729 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 2.218 ms 0 - 13 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 2.094 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 4.05 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 2.589 ms 0 - 7 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 4.889 ms 0 - 15 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 4.73 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.64 ms 0 - 1 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 4.767 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 4.767 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 4.889 ms 0 - 15 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 4.553 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 4.05 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 2.218 ms 0 - 13 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 5.137 ms 0 - 5 MB NPU

License

  • The license for the original implementation of OpusMT-Zh-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