Update app.py

app.py

@@ -3,25 +3,28 @@ import os
 from moviepy.editor import VideoFileClip
 from transformers import pipeline
 
-# ASR (Speech-to-Text) pipeline
+# Load models
 asr = pipeline(task="automatic-speech-recognition", model="distil-whisper/distil-small.en")
-
-# Summarization model
 summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+qa_pipeline = pipeline("question-answering", model="distilbert-base-cased-distilled-squad")
+
+# Global variable to store transcript for Q&A
+stored_transcript = ""
 
 def transcribe_and_summarize(video_file):
+    global stored_transcript
+
     if video_file is None:
         return "Error: No file provided.", ""
 
     try:
-        # Extract audio from the video file
         video = VideoFileClip(video_file)
         audio_path = "temp_audio.wav"
         video.audio.write_audiofile(audio_path, codec='pcm_s16le')
 
-        # Transcribe the extracted audio
         transcription_result = asr(audio_path, return_timestamps=True)
         transcribed_text = " ".join([segment['text'] for segment in transcription_result['chunks']])
+        stored_transcript = transcribed_text  # Save for Q&A
 
         # Summarize
         if len(transcribed_text.split()) < 50:
@@ -35,16 +38,30 @@ def transcribe_and_summarize(video_file):
     except Exception as e:
         return f"Error: {str(e)}", ""
 
-# Create Gradio interface
-iface = gr.Interface(
-    fn=transcribe_and_summarize,
-    inputs=gr.Video(label="Upload Video (.mp4)"),
-    outputs=[
-        gr.Textbox(label="Transcribed Text"),
-        gr.Textbox(label="Summarized Text")
-    ]
-)
-
-# Launch app
+def answer_question(question):
+    global stored_transcript
+    if not stored_transcript:
+        return "Please transcribe a video first."
+    result = qa_pipeline(question=question, context=stored_transcript)
+    return result['answer']
+
+# Gradio interface with three parts
+with gr.Blocks() as iface:
+    with gr.Row():
+        video_input = gr.Video(label="Upload Video (.mp4)")
+        transcribed_text = gr.Textbox(label="Transcribed Text", lines=6)
+        summarized_text = gr.Textbox(label="Summarized Text", lines=6)
+
+    transcribe_btn = gr.Button("Transcribe and Summarize")
+    transcribe_btn.click(fn=transcribe_and_summarize, inputs=video_input, outputs=[transcribed_text, summarized_text])
+
+    with gr.Row():
+        question_input = gr.Textbox(label="Ask a question about the transcript")
+        answer_output = gr.Textbox(label="Answer")
+
+    ask_btn = gr.Button("Get Answer")
+    ask_btn.click(fn=answer_question, inputs=question_input, outputs=answer_output)
+
+# Launch
 port = int(os.environ.get('PORT1', 7860))
 iface.launch(share=True, server_port=port)