diversen/doctr-torch-crnn_vgg16_bn-danish-v1

Optical Character Recognition made seamless & accessible to anyone, powered by TensorFlow 2 & PyTorch

Task: recognition

This model does a good job if you need to do OCR on Danish documents.

Example usage:


from doctr.io import DocumentFile
from doctr.models import ocr_predictor, from_hub

reco_arch = from_hub('diversen/doctr-torch-crnn_vgg16_bn-danish-v1')
det_arch = "db_resnet50"

model = ocr_predictor(det_arch=det_arch, reco_arch=reco_arch, pretrained=True)
image = DocumentFile.from_images(['test.jpg'])

result = model(image)
result.show()

output = result.export()
text_str = ""

for block in output["pages"][0]["blocks"]:
    block_txt = ""
    for line in block["lines"]:
        line_txt = ""
        for word in line["words"]:
            line_txt += word["value"] + " "
        block_txt += line_txt + "\n"
    text_str += block_txt + "\n"

print(text_str)

Run Configuration

{ "arch": "crnn_vgg16_bn", "train_path": "train-data", "val_path": "validation-data", "train_samples": 1000, "val_samples": 20, "font": "FreeMono.ttf,FreeSans.ttf,FreeSerif.ttf", "min_chars": 1, "max_chars": 32, "name": "doctr-torch-crnn_vgg16_bn-danish-v1", "epochs": 1, "batch_size": 64, "device": 0, "input_size": 32, "lr": 0.001, "weight_decay": 0, "workers": 16, "resume": "crnn_vgg16_bn_20240317-095746.pt", "vocab": "danish", "test_only": false, "freeze_backbone": false, "show_samples": false, "wb": false, "push_to_hub": true, "pretrained": true, "sched": "cosine", "amp": false, "find_lr": false, "early_stop": false, "early_stop_epochs": 5, "early_stop_delta": 0.01 }