Hugging Face's logo

qualcomm
/
OpusMT-En-Ko

Text Generation
PyTorch
foundation
android
Model card Files
xet
 Community

OpusMT-En-Ko: Optimized for Qualcomm Devices

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

This is based on the implementation of OpusMT-En-Ko 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-Ko 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-Ko 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-Ko 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-tc-big-en-ko
  • 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 2.904 ms 23 - 30 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 3.161 ms 4 - 11 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 2.552 ms 24 - 24 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 4.387 ms 24 - 24 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 5.984 ms 24 - 33 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 5.88 ms 24 - 51 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.699 ms 24 - 25 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 5.535 ms 24 - 33 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 5.535 ms 24 - 33 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 5.535 ms 24 - 33 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 5.984 ms 24 - 33 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 5.328 ms 24 - 50 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 4.387 ms 24 - 24 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 3.161 ms 4 - 11 MB NPU
decoder VOICE_AI float Qualcomm® SA7255P 7.236 ms 24 - 32 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 6.089 ms 22 - 27 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Extreme Gen 6 Mobile 2.682 ms 24 - 34 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 6 Mobile 2.993 ms 24 - 34 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.962 ms 6 - 14 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.009 ms 0 - 12 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X2 Elite 1.611 ms 5 - 5 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X Elite 2.83 ms 6 - 6 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Gen 1 Mobile 3.78 ms 6 - 15 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 3.646 ms 5 - 14 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.048 ms 6 - 8 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8775P 3.631 ms 6 - 15 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8650P 3.631 ms 6 - 15 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8255P 3.631 ms 6 - 15 MB NPU
decoder VOICE_AI w8a16 Qualcomm® QCS8450 3.78 ms 6 - 15 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 3.451 ms 7 - 15 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 2.83 ms 6 - 6 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 2.009 ms 0 - 12 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA7255P 4.893 ms 6 - 15 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8295P 4.111 ms 4 - 9 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 1.823 ms 6 - 16 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 6 Mobile 1.794 ms 6 - 16 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 5.498 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 6.158 ms 0 - 12 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 5.164 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 9.832 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 12.876 ms 1 - 11 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 10.523 ms 0 - 15 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 10.358 ms 0 - 1 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 10.318 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 10.318 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 10.318 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 12.876 ms 1 - 11 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 10.021 ms 0 - 14 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 9.832 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 6.158 ms 0 - 12 MB NPU
encoder VOICE_AI float Qualcomm® SA7255P 19.646 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 13.398 ms 0 - 5 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Extreme Gen 6 Mobile 2.765 ms 0 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 6 Mobile 5.161 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 5.073 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 5.767 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X2 Elite 4.712 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X Elite 9.119 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Gen 1 Mobile 11.758 ms 0 - 11 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 9.438 ms 0 - 6 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 9.578 ms 0 - 2 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8775P 9.445 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8650P 9.445 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8255P 9.445 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® QCS8450 11.758 ms 0 - 11 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 9.165 ms 0 - 5 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 9.119 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 5.767 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA7255P 18.523 ms 0 - 8 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8295P 12.824 ms 0 - 5 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 2.322 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 6 Mobile 4.749 ms 0 - 9 MB NPU

License

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