Custom Trained OCR model: Mismatch Error in Character Set Size Leading

[geheim01]

Custom Trained OCR model: Mismatch Error in Character Set Size Leading

[geheim01]

Could the error be in the CTCLabelConverter because I use Attn instead of CTC for prediction? and accordingly use the AttnLabelConverter from the deep-text-recognition-benchmark repository in my training?

I looked more into this and it seems that the get_recognizer() function that is called with easyocr.Reader() does not support another LabelConverter next to CTC.

`def get_recognizer(recog_network, network_params, character,
separator_list, dict_list, model_path,
device = 'cpu', quantize = True):

converter = CTCLabelConverter(character, separator_list, dict_list)

num_class = len(converter.character)

if recog_network == 'generation1':
    model_pkg = importlib.import_module("easyocr.model.model")
elif recog_network == 'generation2':
    model_pkg = importlib.import_module("easyocr.model.vgg_model")
else:
    model_pkg = importlib.import_module(recog_network)
model = model_pkg.Model(num_class=num_class, **network_params)

if device == 'cpu':
    state_dict = torch.load(model_path, map_location=device)
    new_state_dict = OrderedDict()
    for key, value in state_dict.items():
        new_key = key[7:]
        new_state_dict[new_key] = value
    model.load_state_dict(new_state_dict)
    if quantize:
        try:
            torch.quantization.quantize_dynamic(model, dtype=torch.qint8, inplace=True)
        except:
            pass

Can't I just use my TPS-ResNet-BiLSTM-Attn Model trained with the deep-text-recognition benchmark model here out of the box with the easyocr package using easy.ocr(recog_network=...)?
If so, what models can I train and use within easyocr?