Hugging Face's logo

qualcomm
/
OpusMT-Ja-En

Text Generation
PyTorch
foundation
android
Model card Files
xet
 Community

OpusMT-Ja-En: Optimized for Qualcomm Devices

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

This is based on the implementation of OpusMT-Ja-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-Ja-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-Ja-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-Ja-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 (Japanese text)
  • Max input sequence length: 256 tokens
  • Max output sequence length: 256 tokens
  • Model checkpoint: Helsinki-NLP/opus-mt-ja-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 1.328 ms 1 - 8 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 1.431 ms 0 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 1.19 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 2.213 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 2.881 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 2.997 ms 12 - 27 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.274 ms 3 - 4 MB NPU
decoder VOICE_AI float Qualcomm® SA8775P 2.967 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 2.967 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 2.967 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 2.881 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 2.777 ms 12 - 27 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 2.213 ms 12 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 1.431 ms 0 - 12 MB NPU
decoder VOICE_AI float Qualcomm® SA7255P 3.977 ms 7 - 16 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 3.042 ms 10 - 15 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Extreme Gen 6 Mobile 1.355 ms 1 - 11 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite Gen 6 Mobile 1.326 ms 1 - 11 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.938 ms 0 - 10 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.977 ms 0 - 13 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X2 Elite 0.941 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Snapdragon® X Elite 1.456 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Gen 1 Mobile 1.651 ms 1 - 10 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 1.89 ms 2 - 6 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.475 ms 0 - 2 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8775P 1.938 ms 1 - 10 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8650P 1.938 ms 1 - 10 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8255P 1.938 ms 1 - 10 MB NPU
decoder VOICE_AI w8a16 Qualcomm® QCS8450 1.651 ms 1 - 10 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 1.795 ms 2 - 5 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.456 ms 3 - 3 MB NPU
decoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 0.977 ms 0 - 13 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA7255P 2.781 ms 3 - 11 MB NPU
decoder VOICE_AI w8a16 Qualcomm® SA8295P 2.118 ms 1 - 6 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.906 ms 0 - 10 MB NPU
decoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 6 Mobile 0.902 ms 0 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.605 ms 0 - 7 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 3.039 ms 0 - 12 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 2.631 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 4.915 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 6.218 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 5.174 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.939 ms 0 - 1 MB NPU
encoder VOICE_AI float Qualcomm® SA8775P 5.219 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 5.219 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 5.219 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 6.218 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 5.069 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 4.915 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 3.039 ms 0 - 12 MB NPU
encoder VOICE_AI float Qualcomm® SA7255P 8.413 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 6.406 ms 0 - 5 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Extreme Gen 6 Mobile 1.139 ms 0 - 10 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 6 Mobile 2.475 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 2.395 ms 0 - 7 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.82 ms 0 - 12 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X2 Elite 2.316 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® X Elite 4.634 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Gen 1 Mobile 5.56 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-8275 4.621 ms 0 - 4 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 4.671 ms 0 - 2 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8775P 4.765 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8650P 4.765 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8255P 4.765 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® QCS8450 5.56 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-9075 4.544 ms 0 - 4 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ IQ-X7181 4.634 ms 0 - 0 MB NPU
encoder VOICE_AI w8a16 Qualcomm® Dragonwing™ Q-8750 2.82 ms 0 - 12 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA7255P 7.875 ms 0 - 9 MB NPU
encoder VOICE_AI w8a16 Qualcomm® SA8295P 6.006 ms 0 - 5 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.927 ms 0 - 10 MB NPU
encoder VOICE_AI w8a16 Snapdragon® 8 Elite Gen 6 Mobile 2.202 ms 0 - 9 MB NPU

License

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