import streamlit as st from transformers import pipeline unmasker = pipeline('fill-mask', model='dsfsi/zabantu-bantu-250m') sample_sentences = { 'Zulu': "Le ndoda ithi izo____ ukudla.", 'Tshivenda': "Mufana uyo____ vhukuma.", 'Sepedi': "Mosadi o ____ pheka.", 'Tswana': "Monna o ____ tsamaya.", 'Tsonga': "N'wana wa xisati u ____ ku tsaka." } def fill_mask_for_languages(sentences): results = {} for language, sentence in sentences.items(): masked_sentence = sentence.replace('____', unmasker.tokenizer.mask_token) unmasked = unmasker(masked_sentence) results[language] = unmasked return results st.title("Fill Mask for Multiple Languages | Zabantu-Bantu-250m") st.write("This app predicts the missing word for sentences in Zulu, Tshivenda, Sepedi, Tswana, and Tsonga using a Zabantu BERT model.") st.write("### Sample sentences:") for language, sentence in sample_sentences.items(): st.write(f"**{language}**: {sentence}") if st.button("Submit"): result = fill_mask_for_languages(sample_sentences) if result: st.write("### Predictions:") for language, predictions in result.items(): original_sentence = sample_sentences[language] predicted_sentence = predictions[0]['sequence'] st.write(f"Original sentence ({language}): {original_sentence}") st.write(f"Top prediction for the masked token: {predicted_sentence}\n") st.write("=" * 80) css = """ """ st.markdown(css, unsafe_allow_html=True)