TrOCR

    Transformer based model for state-of-the-art optical character recognition (OCR) on both printed and handwritten text.

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

    Qualcomm® QCS8550
    QCS8550 (Proxy)
    TorchScriptTFLite
    216ms
    Inference Time
    7-10MB
    Memory Usage
    592NPU
    Layers

    Technical Details

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

    Applicable Scenarios

    • Publishing
    • Healthcare
    • Document Management

    Licenses

    Source Model:MIT
    Deployable Model:AI Model Hub License

    Supported IoT Devices

    • QCS8550 (Proxy)

    Supported IoT Chipsets

    • Qualcomm® QCS8550