OpusMT-Es-En: Optimized for Qualcomm Devices

OpusMT Spanish to English translation model is a state-of-the-art neural machine translation system designed for translating Spanish 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-Es-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-Es-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-Es-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-Es-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 (Spanish text)
  • Max input sequence length: 256 tokens
  • Max output sequence length: 256 tokens
  • Model checkpoint: Helsinki-NLP/opus-mt-es-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 2.375 ms 1 - 8 MB NPU
decoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 2.345 ms 0 - 8 MB NPU
decoder VOICE_AI float Snapdragon® X2 Elite 2.501 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® X Elite 3.19 ms 12 - 12 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 3.005 ms 12 - 20 MB NPU
decoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 4.042 ms 1 - 11 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 4.486 ms 12 - 27 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.437 ms 4 - 6 MB NPU
decoder VOICE_AI float Qualcomm® SA8650P 4.298 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® SA8255P 4.298 ms 12 - 21 MB NPU
decoder VOICE_AI float Qualcomm® QCS8450 4.042 ms 1 - 11 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 4.026 ms 12 - 26 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 3.19 ms 12 - 12 MB NPU
decoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 2.345 ms 0 - 8 MB NPU
decoder VOICE_AI float Qualcomm® SA8295P 4.357 ms 12 - 17 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.734 ms 0 - 7 MB NPU
encoder VOICE_AI float Snapdragon® 8 Elite For Galaxy Mobile 2.202 ms 0 - 8 MB NPU
encoder VOICE_AI float Snapdragon® X2 Elite 2.077 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® X Elite 3.91 ms 0 - 0 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 3 Mobile 2.599 ms 0 - 7 MB NPU
encoder VOICE_AI float Snapdragon® 8 Gen 1 Mobile 4.886 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-8275 4.74 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.636 ms 0 - 1 MB NPU
encoder VOICE_AI float Qualcomm® SA8650P 4.684 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® SA8255P 4.684 ms 0 - 9 MB NPU
encoder VOICE_AI float Qualcomm® QCS8450 4.886 ms 0 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-9075 4.541 ms 2 - 10 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ IQ-X7181 3.91 ms 0 - 0 MB NPU
encoder VOICE_AI float Qualcomm® Dragonwing™ Q-8750 2.202 ms 0 - 8 MB NPU
encoder VOICE_AI float Qualcomm® SA8295P 5.111 ms 0 - 5 MB NPU

License

  • The license for the original implementation of OpusMT-Es-En can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support