Create app.py

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+from transformers import pipeline
+
+summarizer = pipeline(task="summarization", model="t5-small")
+def summarize_text(x,y):
+    return summarizer(x,max_length=y)[0]["summary_text"]
+
+translator = pipeline(task="translation", model="t5-small")
+def translate_text(x):
+    return translator(x)[0]["translation_text"]
+
+classifier = pipeline(task="sentiment-analysis")
+def text_classification(x):
+  preds = classifier(x)
+  return [pred["label"] for pred in preds] 
+
+demo = gr.Blocks()
+
+with demo:
+    gr.Markdown("Language Modeling Tasks")
+    with gr.Tabs():
+        with gr.TabItem("Text Classification"):
+            with gr.Row():
+                tc_input = gr.Textbox(label = "Input Text")
+                tc_output = gr.Textbox(label = "Output")
+            tc_button = gr.Button("Classify")
+        with gr.TabItem("Summarization"):
+            with gr.Row():
+                s_input = gr.Textbox(label = "Input Text")
+                s_output = gr.Textbox(label = "Output Text")
+            s_button = gr.Button("Summarize")
+        with gr.TabItem("Translator"):
+            with gr.Row():
+                translate_input = gr.Textbox(label = "Input Text")
+                translate_output = gr.Textbox(label = "Output Text")
+            translate_button = gr.Button("Translate")
+
+    tc_button.click(text_classification, inputs=tc_input, outputs=tc_output)
+    s_button.click(summarize_text, inputs=s_input, outputs=s_output)
+    translate_button.click(translate_text, inputs=translate_input, outputs=translate_output)
+    
+
+demo.launch(share=True)