Use NLLB 200 for translations

[svenseeberg]

Replace the LLM translations with NLLB-200 3.3B model.

Fix #50

[svenseeberg]

We can use chunking to work around the token limit:

def split_text(text, max_length=500):
    sentences = text.split('.') "

    chunks = []
    current_chunk = ""

    for sentence in sentences:
        if not sentence.strip():
            continue
        sentence = sentence.strip() + "."
        if len(current_chunk) + len(sentence) <= max_length:
            current_chunk += sentence + " " 
        else:
            chunks.append(current_chunk.strip())
            current_chunk = sentence + " "

    if current_chunk.strip():
        chunks.append(current_chunk.strip())

    return chunks