Update app.py

app.py

@@ -19,7 +19,7 @@ nltk.download('averaged_perceptron_tagger')
 # Use faster summarization model
 summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
 
-# Functions
+# Gradio interface
 def extract_audio(video_path):
     video = VideoFileClip(video_path)
     audio_path = "extracted_audio.wav"
@@ -66,8 +66,7 @@ def extract_slide_text(video_path):
     cap.release()
     return "\n\n".join(ocr_texts)
 
-# Gradio UI
-def process_file(uploaded_file):
+def process_uploaded_file(uploaded_file):
     with tempfile.NamedTemporaryFile(delete=False, suffix=uploaded_file.name) as temp_file:
         temp_file.write(uploaded_file.read())
         file_path = temp_file.name
@@ -80,37 +79,44 @@ def process_file(uploaded_file):
             audio_path = extract_audio(file_path)
 
         with concurrent.futures.ThreadPoolExecutor() as executor:
-            # Running OCR and transcription in parallel
+            st.info("🚀 Running OCR and transcription in parallel...")
             ocr_future = executor.submit(extract_slide_text, file_path) if file_path.endswith((".mp4", ".mov", ".avi", ".mkv")) else None
             trans_future = executor.submit(transcribe_audio, audio_path)
 
             transcript = trans_future.result()
             slide_text = ocr_future.result() if ocr_future else ""
 
-        results = {}
+        return transcript, slide_text
 
-        if slide_text:
-            results["slide_text"] = slide_text
-
-        results["transcript"] = transcript
-        results["keywords"] = extract_keywords(transcript)
-        summary_mode = "short"
-        results["summary"] = summarize_text(transcript, ratio=summary_mode)
+    except Exception as e:
+        return f"🚫 Error: {e}", ""
 
+    finally:
         os.remove(file_path)
         if audio_path != file_path and os.path.exists(audio_path):
             os.remove(audio_path)
 
-        return results
+# Gradio Interface for input and output
+def generate_notes(uploaded_file):
+    transcript, slide_text = process_uploaded_file(uploaded_file)
+
+    if slide_text:
+        slide_text_display = f"🖼️ Slide/Whiteboard Extracted Text: \n{slide_text}"
+    else:
+        slide_text_display = "No slide/whiteboard text extracted."
+
+    if len(transcript.split()) < 30:
+        transcript_display = "Transcript too short for a meaningful summary."
+    else:
+        summary_mode = "short"  # Default summary mode
+        summary = summarize_text(transcript, ratio=summary_mode)
+        transcript_display = f"📜 Full Transcription: \n{transcript}\n\n📋 Lecture Summary: \n{summary}"
+
+    return slide_text_display, transcript_display
+
 
 # Gradio Interface
 inputs = gr.File(label="Upload Audio/Video File (Any Format)", type="file")
-outputs = [
-    gr.Textbox(label="Full Transcription", lines=10),
-    gr.Textbox(label="Keywords", lines=2),
-    gr.Textbox(label="Lecture Summary", lines=10),
-    gr.Textbox(label="Slide/Whiteboard Text", lines=10)
-]
-
-gr.Interface(fn=process_file, inputs=inputs, outputs=outputs, live=True).launch()
+outputs = [gr.Textbox(label="Slide Text"), gr.Textbox(label="Lecture Transcript and Summary")]
 
+gr.Interface(fn=generate_notes, inputs=inputs, outputs=outputs, live=True).launch()