import gradio as gr from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline import csv MODEL_URL = "https://huggingface.co/dsfsi/PuoBERTa-News" WEBSITE_URL = "https://www.kodiks.com/ai_solutions.html" tokenizer = AutoTokenizer.from_pretrained("dsfsi/PuoBERTa-News") model = AutoModelForSequenceClassification.from_pretrained("dsfsi/PuoBERTa-News") categories = { "arts_culture_entertainment_and_media": "Botsweretshi, setso, boitapoloso le bobegakgang", "crime_law_and_justice": "Bosenyi, molao le bosiamisi", "disaster_accident_and_emergency_incident": "Masetlapelo, kotsi le tiragalo ya maemo a tshoganyetso", "economy_business_and_finance": "Ikonomi, tsa kgwebo le tsa ditšhelete", "education": "Thuto", "environment": "Tikologo", "health": "Boitekanelo", "politics": "Dipolotiki", "religion_and_belief": "Bodumedi le tumelo", "society": "Setšhaba" } with gr.Row(): gr.Column() gr.Column(gr.Image("logo_transparent_small.png", alt="DSFSI Logo", elem_id="logo", label=None)) gr.Column() description = """

Setswana News Classification

This space provides a classification service for news in Setswana.

""" article = """
GitHub | Feedback Form
""" def prediction(news): classifier = pipeline("text-classification", tokenizer=tokenizer, model=model, return_all_scores=True) preds = classifier(news) preds_dict = {categories.get(pred['label'], pred['label']): round(pred['score'], 4) for pred in preds[0]} return preds_dict def file_prediction(file): news_list = [] if file.name.endswith('.csv'): file.seek(0) reader = csv.reader(file.read().decode('utf-8').splitlines()) news_list = [row[0] for row in reader if row] else: file.seek(0) file_content = file.read().decode('utf-8') news_list = file_content.splitlines() results = [] for news in news_list: if news.strip(): pred = prediction(news) results.append([news, pred]) return results gradio_ui = gr.Interface( fn=prediction, title="Setswana News Classification", description=f"Enter Setswana news article to see the category of the news.\n For this classification, the {MODEL_URL} model was used.", inputs=gr.Textbox(lines=10, label="Paste some Setswana news here"), outputs=gr.Label(num_top_classes=5, label="News categories probabilities"), theme="default", article="

For our other AI works: https://www.kodiks.com/ai_solutions.html | Contact us

", ) gradio_file_ui = gr.Interface( fn=file_prediction, title="Upload File for Setswana News Classification", description=f"Upload a text or CSV file with Setswana news articles. The first column in the CSV should contain the news text.", inputs=gr.File(label="Upload text or CSV file"), outputs=gr.Dataframe(headers=["News Text", "Category Predictions"], label="Predictions from file"), theme="default" ) authors = """
Authors: Vukosi Marivate and Moseli Mots'Oehli and Valencia Wagner and Richard Lastrucci and Isheanesu Dzingirai
""" citation = """ @inproceedings{marivate2023puoberta, title = {PuoBERTa: Training and evaluation of a curated language model for Setswana}, author = {Vukosi Marivate and Moseli Mots'Oehli and Valencia Wagner and Richard Lastrucci and Isheanesu Dzingirai}, year = {2023}, booktitle= {Artificial Intelligence Research. SACAIR 2023. Communications in Computer and Information Science}, url= {https://link.springer.com/chapter/10.1007/978-3-031-49002-6_17}, keywords = {NLP}, preprint_url = {https://arxiv.org/abs/2310.09141}, dataset_url = {https://github.com/dsfsi/PuoBERTa}, software_url = {https://huggingface.co/dsfsi/PuoBERTa} } """ doi = """
DOI: 10.1007/978-3-031-49002-6_17
""" gradio_combined_ui = gr.TabbedInterface([gradio_ui, gradio_file_ui], ["Text Input", "File Upload"]) gradio_combined_ui.launch()