Create app.py

app.py

@@ -0,0 +1,57 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+
+model_id = "xlm-roberta-base"
+peft_model_id = "rasyosef/xlm-roberta-base-lora-amharic-news-classification"
+
+categories = ['ሀገር አቀፍ ዜና', 'መዝናኛ', 'ስፖርት', 'ቢዝነስ', 'ዓለም አቀፍ ዜና', 'ፖለቲካ']
+id2label = {i: lbl for i, lbl in enumerate(categories)}
+label2id = {lbl: i for i, lbl in enumerate(categories)}
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+model = AutoModelForSequenceClassification.from_pretrained(
+    model_id,
+    num_labels=len(categories), # 6
+    id2label=id2label,
+    label2id=label2id
+)
+
+model.load_adapter(peft_model_id)
+
+classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
+
+def predict(text):
+    return classifier([text])[0]
+
+
+with gr.Blocks() as demo:
+    gr.Markdown(
+        """
+        # Amharic News Article Classification 
+        This is A finetuned RoBERTa model (xlm-roberta-base) that classifies amharic news articles into one of 6 categories.
+        - ሀገር አቀፍ ዜና (Local News)
+        - መዝናኛ (Entertainment)
+        - ስፖርት (Sports)
+        - ቢዝነስ (Business)
+        - ዓለም አቀፍ ዜና (International News)
+        - ፖለቲካ (Politics)
+        """
+    )
+
+    with gr.Row():
+        with gr.Column():
+            input = gr.Textbox(label="Amharic text")
+            classify_btn = gr.Button(value="Classify")
+        with gr.Column():
+            output = gr.Textbox(label="Predicted class")
+
+    classify_btn.click(predict, inputs=input, outputs=output)
+    examples = gr.Examples(
+        examples=[
+            """በአፄ ቴዎድሮስ የንግስና ቦታ ደረስጌ ማሪያም ተጀምሮ የቆመው የሙዚየሙ ግንባታ ተጠናቀቆ ስራ እንዲጀምር ነዋሪዎች ጠይቀዋል። ዘመነ መሳፍንት መቋጫ ያገኘባት የኢትዮጵያ አንድነት የታወጀባት ዳግማዊ አፄ ቴዎድሮስ ከመንገሳቸው በፊት ደጃች ውቤን ቧሂት ከሚባል ቦታ ድል አድርገው ደጃች ውቤ ለንግስና ባዘጋጁት የንግስና ቦታና እቃዎች ንጉሰ ነገስት ዘኢትዮጵያ ተብለው የነገሱባት ቦታ ናት።"""
+        ],
+        inputs=[input],
+    )
+
+demo.launch()