Hugging Face's logo

qualcomm
/
OpusMT-En-Zh

Text Generation
PyTorch
foundation
android
Model card Files
xet
 Community

OpusMT-En-Zh: Optimized for Qualcomm Devices

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

This is based on the implementation of OpusMT-En-Zh 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.

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 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 Qualcomm® QCS8550 (Proxy) QAIRT 2.45 Download
VOICE_AI float Qualcomm® SA8775P QAIRT 2.45 Download
VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 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 Qualcomm® QCS9075 QAIRT 2.45 Download
VOICE_AI float Qualcomm® QCS8450 (Proxy) QAIRT 2.45 Download

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

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

  • Model checkpoint: Helsinki-NLP/opus-mt-en-zh
  • Input resolution: 256 tokens (English text)
  • Max input sequence length: 256 tokens
  • Max output sequence length: 256 tokens
  • Number of parameters (encoder): ~74M
  • Model size (encoder) (float): ~280 MB
  • Number of parameters (decoder): ~74M
  • Model size (decoder) (float): ~280 MB
  • Number of encoder layers: 6
  • Number of decoder layers: 6
  • Attention heads: 8
  • Hidden dimension: 512

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 Mobile 2.181 ms 1 - 11 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Mobile 2.553 ms 0 - 13 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 2.146 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 3.075 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 3.075 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 2.766 ms 0 - 8 MB NPU
decoder VOICE_AI float Qualcomm® QCS8275 (Proxy) 6.712 ms 12 - 20 MB NPU
decoder VOICE_AI float Qualcomm® QCS8550 (Proxy) 3.457 ms 12 - 14 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 4.202 ms 12 - 20 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 4.202 ms 12 - 20 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 4.202 ms 12 - 20 MB NPU
decoder VOICE_AI float Qualcomm® QCS9075 3.962 ms 12 - 26 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 (Proxy) 4.501 ms 12 - 22 MB NPU
decoder VOICE_AI float Qualcomm® SA7255P 6.712 ms 12 - 20 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 4.467 ms 10 - 16 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 2.553 ms 0 - 13 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 Mobile 1.77 ms 0 - 9 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Mobile 2.225 ms 0 - 14 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 2.073 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 3.974 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 3.974 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 2.639 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® QCS8275 (Proxy) 12.634 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® QCS8550 (Proxy) 3.644 ms 0 - 2 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 4.748 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 4.748 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 4.748 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® QCS9075 4.566 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 (Proxy) 5.034 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® SA7255P 12.634 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 5.393 ms 0 - 6 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 2.225 ms 0 - 14 MB NPU

License

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