sam749/donut-base-finetuned-sroie-v2

from transformers import DonutProcessor, VisionEncoderDecoderModel

device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float16 if torch.cuda.is_available() else torch.float32

processor = DonutProcessor.from_pretrained("sam749/donut-base-finetuned-sroie-v2")
model = VisionEncoderDecoderModel.from_pretrained("sam749/donut-base-finetuned-sroie-v2", dtype=dtype)
model.to(device)

def generate(image):
    # prepare encoder inputs
    pixel_values = processor(image, return_tensors="pt").pixel_values
    
    # generate answer
    outputs = model.generate(
        pixel_values.to(device),
        use_cache=True,
        num_beams=1,
        bad_words_ids=[[processor.tokenizer.unk_token_id]],
        return_dict_in_generate=True,
    )
    
    # postprocess
    sequence = processor.batch_decode(outputs.sequences)[0]
    sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
    sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove first task start token
    
    return processor.token2json(sequence)