|
import gradio as gr |
|
from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline |
|
|
|
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" |
|
} |
|
|
|
def prediction(news): |
|
clasifer = pipeline("sentiment-analysis", tokenizer=tokenizer, model=model, return_all_scores=True) |
|
|
|
preds = clasifer(news) |
|
|
|
preds_dict = {} |
|
for pred in preds[0]: |
|
label = categories.get(pred['label'], pred['label']) |
|
preds_dict[label] = pred['score'] |
|
|
|
return preds_dict |
|
|
|
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.", |
|
examples=[ |
|
['Ka Letsatsi la Aforika, Aforika Borwa e tla be e keteka mabaka a boikemelo, le diketso tse di siameng tse e di dirileng go tokafatsa dikamano tsa yona le dinaga tse dingwe tsa Aforika.'], |
|
["Thuto ya Setswana ke nngwe ya dithuto tse di botlhokwa mo sekolong se se tlhamaletseng go ruta bana ba ba mo lefatsheng la Botswana."], |
|
["Mo kgweding e e fetileng, dipuisano tsa ditheko tsa dijalo di ile tsa tswelela, ka batho ba rekang le barui ba ba ruileng."], |
|
["Masole a Aforika Borwa a ne a ya kwa Mozambique go tlisetsa motlakase morago ga maduo a kgatlha."], |
|
], |
|
inputs=gr.inputs.Textbox(lines=10, label="Paste some Setswana news here"), |
|
outputs=gr.outputs.Label(num_top_classes=5, type="auto", label="News categories probabilities"), |
|
theme="huggingface", |
|
article="<p style='text-align: center'>For our other AI works: <a href='https://www.kodiks.com/ai_solutions.html' target='_blank'>https://www.kodiks.com/ai_solutions.html</a> | <a href='https://twitter.com/KodiksBilisim' target='_blank'>Contact us</a></p>", |
|
) |
|
|
|
gradio_ui.launch() |
|
|