from transformers import T5ForConditionalGeneration, T5Tokenizer


def do_inference(text, model, tokenizer):
    input_text = f"denoise: {text}"
    inputs = tokenizer.encode(
        input_text,
        return_tensors="pt",
        max_length=256,
        padding="max_length",
        truncation=True,
    )

    corrected_ids = model.generate(
        inputs,
        max_length=256,
        num_beams=5,
        early_stopping=True,
    )

    corrected_sentence = tokenizer.decode(corrected_ids[0], skip_special_tokens=True)
    return corrected_sentence


model = T5ForConditionalGeneration.from_pretrained("radlab/polish-denoiser-t5-base")
tokenizer = T5Tokenizer.from_pretrained("radlab/polish-denoiser-t5-base")

text_str = "As | -Tron^# om ia je@st je!d &*ną z na -J s | AA ta rsZy ch n a u   k."
print(do_inference(text_str, model, tokenizer))

Model reponse for input:

denoise: As | -Tron^# om ia je@st je!d &*ną z na -J s | AA ta rsZy ch n a u k.

is:

Astronomia jest jedną z najstarszych nauk.

Evaluation

Eval loss:

More information (in Polish) on our blog