import re from PIL import Image def clean_text(text): text = re.sub(r"<[^>]+>", "", text) # Remove HTML text = re.sub(r"[^a-zA-ZÀ-ÿ0-9\s]", "", text) # Remove caracteres especiais return text.strip() def resize_image(image, size=(224, 224)): return image.resize(size) def normalize_audio(audio_array): return audio_array / max(abs(audio_array))