# TrOCR

URL: https://interfaze.ai/models/qualcommtrocr

[All models](https://interfaze.ai/models)

TrOCR by qualcomm, a image-to-text model with OCR capabilities. Understand and compare OCR features, benchmarks, and capabilities.

## Comparison

| Feature | TrOCR | Interfaze |
| --- | --- | --- |
| Input Modalities | image | image, text, audio, video, document |
| Native OCR | Yes | Yes |
| Long Document Processing | No | Yes |
| Language Support | unknown | 162+ |
| Native Speech-to-Text | No | Yes |
| Native Object Detection | No | Yes |
| Guardrail Controls | No | Yes |
| Context Input Size | unknown | 1M |
| Tool Calling | No | Tool calling supported + built in browser, code execution and web search |

### OCR Capabilities

| Feature | TrOCR | Interfaze |
| --- | --- | --- |
| Text Bounding Boxes | No | Yes |
| Confidence Scores | No | Yes |
| Dense Image Processing | No | Yes |
| Low Quality Images | No | Yes |
| Handwritten Text | Yes | Yes |
| Charts, Tables & Equations | No | Yes |

### Scaling

| Feature | TrOCR | Interfaze |
| --- | --- | --- |
| Scaling | Self-hosted/Provider-hosted with quantization | Unlimited |

[Try Interfaze](https://interfaze.ai/dashboard)[Read the Docs](https://interfaze.ai/docs)

View model card on [Hugging Face](https://huggingface.co/qualcomm/TrOCR)

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/web-assets/model_demo.png)

End-to-end text recognition approach with pre-trained image transformer and text transformer models for both image understanding and wordpiece-level text generation.

This is based on the implementation of TrOCR found [here](https://huggingface.co/microsoft/trocr-small-stage1). This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/trocr) library to export with custom configurations. More details on model performance across various devices, can be found [here](https://interfaze.ai/models/qualcommtrocr#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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 1.24.3 | Download |
| QNN\_DLC | float | Universal | QAIRT 2.43 | Download |
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.19.1 | Download |

For more device-specific assets and performance metrics, visit **[TrOCR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/trocr)**.

### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/trocr) 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 [TrOCR on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/trocr) for usage instructions.

## Model Details

**Model Type:** Model\_use\_case.image\_to\_text

**Model Stats:**

-   Model checkpoint: trocr-small-stage1
-   Input resolution: 320x320
-   Number of parameters (decoder): 38.3M
-   Model size (decoder) (float): 146 MB
-   Number of parameters (encoder): 23.0M
-   Model size (encoder) (float): 87.8 MB

## Performance Summary

| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
| --- | --- | --- | --- | --- | --- | --- |
| decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.142 ms | 0 - 224 MB | NPU |
| decoder | ONNX | float | Snapdragon® X2 Elite | 1.153 ms | 68 - 68 MB | NPU |
| decoder | ONNX | float | Snapdragon® X Elite | 2.348 ms | 67 - 67 MB | NPU |
| decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.456 ms | 0 - 258 MB | NPU |
| decoder | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.138 ms | 1 - 4 MB | NPU |
| decoder | ONNX | float | Qualcomm® QCS9075 | 2.714 ms | 7 - 16 MB | NPU |
| decoder | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.248 ms | 0 - 252 MB | NPU |
| decoder | QNN\_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.117 ms | 1 - 212 MB | NPU |
| decoder | QNN\_DLC | float | Snapdragon® X2 Elite | 1.6 ms | 7 - 7 MB | NPU |
| decoder | QNN\_DLC | float | Snapdragon® X Elite | 2.141 ms | 7 - 7 MB | NPU |
| decoder | QNN\_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.403 ms | 0 - 232 MB | NPU |
| decoder | QNN\_DLC | float | Qualcomm® QCS8275 (Proxy) | 4.216 ms | 7 - 143 MB | NPU |
| decoder | QNN\_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.952 ms | 1 - 3 MB | NPU |
| decoder | QNN\_DLC | float | Qualcomm® SA8775P | 2.833 ms | 7 - 144 MB | NPU |
| decoder | QNN\_DLC | float | Qualcomm® QCS9075 | 2.549 ms | 7 - 16 MB | NPU |
| decoder | QNN\_DLC | float | Qualcomm® QCS8450 (Proxy) | 2.869 ms | 1 - 215 MB | NPU |
| decoder | QNN\_DLC | float | Qualcomm® SA7255P | 4.216 ms | 7 - 143 MB | NPU |
| decoder | QNN\_DLC | float | Qualcomm® SA8295P | 2.934 ms | 7 - 130 MB | NPU |
| decoder | QNN\_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.236 ms | 0 - 226 MB | NPU |
| decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.097 ms | 0 - 224 MB | NPU |
| decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.36 ms | 0 - 247 MB | NPU |
| decoder | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.235 ms | 0 - 155 MB | NPU |
| decoder | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.939 ms | 0 - 3 MB | NPU |
| decoder | TFLITE | float | Qualcomm® SA8775P | 2.799 ms | 0 - 151 MB | NPU |
| decoder | TFLITE | float | Qualcomm® QCS9075 | 2.514 ms | 0 - 83 MB | NPU |
| decoder | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 2.575 ms | 0 - 225 MB | NPU |
| decoder | TFLITE | float | Qualcomm® SA7255P | 4.235 ms | 0 - 155 MB | NPU |
| decoder | TFLITE | float | Qualcomm® SA8295P | 3.039 ms | 0 - 134 MB | NPU |
| decoder | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.164 ms | 0 - 231 MB | NPU |
| encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.389 ms | 1 - 178 MB | NPU |
| encoder | ONNX | float | Snapdragon® X2 Elite | 4.863 ms | 48 - 48 MB | NPU |
| encoder | ONNX | float | Snapdragon® X Elite | 12.577 ms | 47 - 47 MB | NPU |
| encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 8.29 ms | 16 - 269 MB | NPU |
| encoder | ONNX | float | Qualcomm® QCS8550 (Proxy) | 11.99 ms | 0 - 60 MB | NPU |
| encoder | ONNX | float | Qualcomm® QCS9075 | 15.758 ms | 15 - 19 MB | NPU |
| encoder | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 5.752 ms | 16 - 190 MB | NPU |
| encoder | QNN\_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.662 ms | 2 - 156 MB | NPU |
| encoder | QNN\_DLC | float | Snapdragon® X2 Elite | 5.659 ms | 2 - 2 MB | NPU |
| encoder | QNN\_DLC | float | Snapdragon® X Elite | 12.47 ms | 2 - 2 MB | NPU |
| encoder | QNN\_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.248 ms | 0 - 231 MB | NPU |
| encoder | QNN\_DLC | float | Qualcomm® QCS8275 (Proxy) | 38.122 ms | 2 - 149 MB | NPU |
| encoder | QNN\_DLC | float | Qualcomm® QCS8550 (Proxy) | 11.819 ms | 2 - 3 MB | NPU |
| encoder | QNN\_DLC | float | Qualcomm® SA8775P | 14.225 ms | 2 - 149 MB | NPU |
| encoder | QNN\_DLC | float | Qualcomm® QCS9075 | 16.741 ms | 2 - 12 MB | NPU |
| encoder | QNN\_DLC | float | Qualcomm® QCS8450 (Proxy) | 21.927 ms | 0 - 345 MB | NPU |
| encoder | QNN\_DLC | float | Qualcomm® SA7255P | 38.122 ms | 2 - 149 MB | NPU |
| encoder | QNN\_DLC | float | Qualcomm® SA8295P | 20.266 ms | 2 - 273 MB | NPU |
| encoder | QNN\_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 5.765 ms | 2 - 155 MB | NPU |
| encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.067 ms | 0 - 145 MB | NPU |
| encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 7.719 ms | 6 - 227 MB | NPU |
| encoder | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 36.775 ms | 7 - 145 MB | NPU |
| encoder | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 10.703 ms | 7 - 9 MB | NPU |
| encoder | TFLITE | float | Qualcomm® SA8775P | 13.375 ms | 7 - 146 MB | NPU |
| encoder | TFLITE | float | Qualcomm® QCS9075 | 13.963 ms | 6 - 65 MB | NPU |
| encoder | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 19.604 ms | 7 - 340 MB | NPU |
| encoder | TFLITE | float | Qualcomm® SA7255P | 36.775 ms | 7 - 145 MB | NPU |
| encoder | TFLITE | float | Qualcomm® SA8295P | 19.123 ms | 7 - 269 MB | NPU |
| encoder | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 5.219 ms | 5 - 153 MB | NPU |

## License

-   The license for the original implementation of TrOCR can be found [here](https://github.com/microsoft/unilm/blob/master/LICENSE).

## References

-   [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://arxiv.org/abs/2109.10282)
-   [Source Model Implementation](https://huggingface.co/microsoft/trocr-small-stage1)

## Community

-   Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
-   For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).

## Want more deterministic results?

[Try Interfaze](https://interfaze.ai/dashboard)[Read the Docs](https://interfaze.ai/docs)