Hugging Face's logo

qualcomm
/
OpusMT-Es-En

Text Generation
PyTorch
foundation
android
Model card Files
xet
Community

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.

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
ONNX float Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
QNN_CONTEXT_BINARY float qualcomm-qcs8275 QAIRT 2.42 Download
QNN_DLC float Universal QAIRT 2.43 Download
TFLITE float Universal QAIRT 2.43, TFLite 2.17.0 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:

  • Model checkpoint: Helsinki-NLP/opus-mt-es-en
  • Input resolution: 256 tokens (Spanish text)
  • Max input sequence length: 256 tokens
  • Max output sequence length: 256 tokens
  • Number of parameters (OpusMTEncoder): ~74M
  • Model size (OpusMTEncoder) (float): ~280 MB
  • Number of parameters (OpusMTDecoder): ~74M
  • Model size (OpusMTDecoder) (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
OpusMTDecoder ONNX float Snapdragon® X2 Elite 1.755 ms 161 - 161 MB NPU
OpusMTDecoder ONNX float Snapdragon® X Elite 3.141 ms 160 - 160 MB NPU
OpusMTDecoder ONNX float Snapdragon® 8 Gen 3 Mobile 2.754 ms 0 - 397 MB NPU
OpusMTDecoder ONNX float Qualcomm® QCS8550 (Proxy) 3.52 ms 12 - 22 MB NPU
OpusMTDecoder ONNX float Qualcomm® QCS9075 4.267 ms 12 - 27 MB NPU
OpusMTDecoder ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.366 ms 0 - 428 MB NPU
OpusMTDecoder ONNX float Snapdragon® 8 Elite Gen 5 Mobile 2.215 ms 1 - 378 MB NPU
OpusMTDecoder QNN_DLC float Snapdragon® X2 Elite 2.006 ms 6 - 6 MB NPU
OpusMTDecoder QNN_DLC float Snapdragon® X Elite 3.067 ms 6 - 6 MB NPU
OpusMTDecoder QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.479 ms 0 - 189 MB NPU
OpusMTDecoder QNN_DLC float Qualcomm® QCS8275 (Proxy) 6.812 ms 2 - 167 MB NPU
OpusMTDecoder QNN_DLC float Qualcomm® QCS8550 (Proxy) 3.09 ms 2 - 4 MB NPU
OpusMTDecoder QNN_DLC float Qualcomm® SA8775P 3.942 ms 2 - 168 MB NPU
OpusMTDecoder QNN_DLC float Qualcomm® QCS9075 3.373 ms 6 - 14 MB NPU
OpusMTDecoder QNN_DLC float Qualcomm® QCS8450 (Proxy) 3.989 ms 2 - 168 MB NPU
OpusMTDecoder QNN_DLC float Qualcomm® SA7255P 6.812 ms 2 - 167 MB NPU
OpusMTDecoder QNN_DLC float Qualcomm® SA8295P 4.12 ms 6 - 157 MB NPU
OpusMTDecoder QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 2.148 ms 0 - 164 MB NPU
OpusMTDecoder QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.891 ms 0 - 171 MB NPU
OpusMTDecoder TFLITE float Snapdragon® 8 Gen 3 Mobile 2.981 ms 0 - 383 MB NPU
OpusMTDecoder TFLITE float Qualcomm® QCS8275 (Proxy) 6.67 ms 0 - 230 MB NPU
OpusMTDecoder TFLITE float Qualcomm® QCS8550 (Proxy) 3.413 ms 0 - 2 MB NPU
OpusMTDecoder TFLITE float Qualcomm® SA8775P 4.22 ms 0 - 230 MB NPU
OpusMTDecoder TFLITE float Qualcomm® QCS9075 4.217 ms 0 - 186 MB NPU
OpusMTDecoder TFLITE float Qualcomm® QCS8450 (Proxy) 4.727 ms 0 - 355 MB NPU
OpusMTDecoder TFLITE float Qualcomm® SA7255P 6.67 ms 0 - 230 MB NPU
OpusMTDecoder TFLITE float Qualcomm® SA8295P 4.903 ms 0 - 212 MB NPU
OpusMTDecoder TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 2.477 ms 0 - 414 MB NPU
OpusMTDecoder TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.144 ms 0 - 374 MB NPU
OpusMTEncoder ONNX float Snapdragon® X2 Elite 2.219 ms 108 - 108 MB NPU
OpusMTEncoder ONNX float Snapdragon® X Elite 5.011 ms 108 - 108 MB NPU
OpusMTEncoder ONNX float Snapdragon® 8 Gen 3 Mobile 3.422 ms 0 - 265 MB NPU
OpusMTEncoder ONNX float Qualcomm® QCS8550 (Proxy) 4.735 ms 0 - 115 MB NPU
OpusMTEncoder ONNX float Qualcomm® QCS9075 6.195 ms 16 - 18 MB NPU
OpusMTEncoder ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.769 ms 0 - 293 MB NPU
OpusMTEncoder ONNX float Snapdragon® 8 Elite Gen 5 Mobile 2.028 ms 0 - 257 MB NPU
OpusMTEncoder QNN_DLC float Snapdragon® X2 Elite 1.984 ms 0 - 0 MB NPU
OpusMTEncoder QNN_DLC float Snapdragon® X Elite 3.866 ms 0 - 0 MB NPU
OpusMTEncoder QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.546 ms 0 - 86 MB NPU
OpusMTEncoder QNN_DLC float Qualcomm® QCS8275 (Proxy) 12.611 ms 0 - 52 MB NPU
OpusMTEncoder QNN_DLC float Qualcomm® QCS8550 (Proxy) 3.453 ms 0 - 2 MB NPU
OpusMTEncoder QNN_DLC float Qualcomm® SA8775P 4.535 ms 0 - 53 MB NPU
OpusMTEncoder QNN_DLC float Qualcomm® QCS9075 4.676 ms 0 - 5 MB NPU
OpusMTEncoder QNN_DLC float Qualcomm® QCS8450 (Proxy) 4.716 ms 0 - 86 MB NPU
OpusMTEncoder QNN_DLC float Qualcomm® SA7255P 12.611 ms 0 - 52 MB NPU
OpusMTEncoder QNN_DLC float Qualcomm® SA8295P 5.355 ms 0 - 54 MB NPU
OpusMTEncoder QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 2.138 ms 0 - 53 MB NPU
OpusMTEncoder QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.614 ms 0 - 58 MB NPU
OpusMTEncoder TFLITE float Snapdragon® 8 Gen 3 Mobile 2.645 ms 0 - 256 MB NPU
OpusMTEncoder TFLITE float Qualcomm® QCS8275 (Proxy) 12.873 ms 6 - 99 MB NPU
OpusMTEncoder TFLITE float Qualcomm® QCS8550 (Proxy) 3.671 ms 0 - 2 MB NPU
OpusMTEncoder TFLITE float Qualcomm® SA8775P 19.476 ms 6 - 100 MB NPU
OpusMTEncoder TFLITE float Qualcomm® QCS9075 5.143 ms 4 - 119 MB NPU
OpusMTEncoder TFLITE float Qualcomm® QCS8450 (Proxy) 5.08 ms 6 - 258 MB NPU
OpusMTEncoder TFLITE float Qualcomm® SA7255P 12.873 ms 6 - 99 MB NPU
OpusMTEncoder TFLITE float Qualcomm® SA8295P 5.681 ms 6 - 95 MB NPU
OpusMTEncoder TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 2.241 ms 0 - 271 MB NPU
OpusMTEncoder TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.762 ms 0 - 243 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
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support