Update app.py

app.py

@@ -2,6 +2,8 @@ import gradio as gr
 import whisper
 from pytube import YouTube
 from transformers import pipeline, T5Tokenizer, T5ForConditionalGeneration, AutoTokenizer, AutoModelForSeq2SeqLM
+from wordcloud import WordCloud
+import matplotlib.pyplot as plt
 
 class GradioInference():
     def __init__(self):
@@ -75,8 +77,9 @@ class GradioInference():
         keywords = [x.strip() for x in predicted.split(',') if x.strip()]
 
         label = self.classifier(results["text"])[0]["label"]
+        wordcloud = WordCloud(width=800, height=400, background_color='white').generate(results["text"])
         
-        return results["text"], transcription_summary[0]["summary_text"], keywords, label
+        return results["text"], transcription_summary[0]["summary_text"], keywords, label, wordcloud
 
 
 gio = GradioInference()
@@ -112,10 +115,13 @@ with block as demo:
                     summary = gr.Textbox(label="Summary", placeholder="Summary Output...", lines=5).style(show_copy_button=True, container=True)
                     keywords = gr.Textbox(label="Keywords", placeholder="Keywords Output...", lines=5).style(show_copy_button=True, container=True)
                     label = gr.Label(label="Sentiment Analysis")
+                with gr.Row().style(equal_height=True):    
+                    # Display the Word Cloud
+                    wordcloud = gr.Image()
                 with gr.Row().style(equal_height=True):
                     clear = gr.ClearButton([link, title, img, text, summary, keywords, label], scale=1)
                     btn = gr.Button("Get video insights", variant='primary', scale=1)
-                btn.click(gio, inputs=[link, lang, size], outputs=[text, summary, keywords, label])
+                btn.click(gio, inputs=[link, lang, size], outputs=[text, summary, keywords, label, wordcloud])
                 link.change(gio.populate_metadata, inputs=[link], outputs=[img, title])
 
         with gr.Tab("From Audio file"):