Create app.py

app.py

@@ -0,0 +1,85 @@
+import gradio as gr
+import os
+import torch
+import whisper
+from transformers import pipeline
+from moviepy.editor import VideoFileClip
+
+# Function to extract audio from a video file
+def extract_audio(video_path, audio_path="audio.wav"):
+    if os.path.exists(audio_path):
+        os.remove(audio_path)
+    video = VideoFileClip(video_path)
+    video.audio.write_audiofile(audio_path, codec='pcm_s16le', bitrate='32k')  # Lower bitrate for faster processing
+    return audio_path
+
+# Function to transcribe audio using Whisper
+def transcribe_audio(audio_path):
+    try:
+        model = whisper.load_model("tiny")  # Faster model
+        result = model.transcribe(audio_path)
+        return result["text"]
+    except Exception as e:
+        return f"Error in transcription: {str(e)}"
+
+# Function to summarize text using a pre-trained transformer model
+def summarize_text(text):
+    try:
+        summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
+        max_chunk_size = 300  # Reduced chunk size for faster processing
+        chunks = [text[i:i + max_chunk_size] for i in range(0, len(text), max_chunk_size)]
+        summaries = [summarizer(chunk, max_length=80, min_length=20, do_sample=False)[0]["summary_text"] for chunk in chunks]
+        return " ".join(summaries)
+    except Exception as e:
+        return f"Error in summarization: {str(e)}"
+
+# Function to generate study notes using GPT-2
+def generate_study_notes(summary):
+    try:
+        generator = pipeline("text-generation", model="gpt2")
+        prompt = f"Create concise study notes from this summary:\n{summary}"
+        study_notes = generator(prompt, max_length=150, num_return_sequences=1, truncation=True)
+        return study_notes[0]["generated_text"]
+    except Exception as e:
+        return f"Error in generating study notes: {str(e)}"
+
+# Function to answer questions using a QA model
+def answer_question(question, context):
+    try:
+        qa_pipeline = pipeline("question-answering", model="distilbert-base-uncased-distilled-squad")
+        result = qa_pipeline(question=question, context=context)
+        return result["answer"]
+    except Exception as e:
+        return f"Error in answering question: {str(e)}"
+
+# Gradio UI
+def process_video(video_file):
+    video_path = video_file  # Directly using filepath
+    audio_path = extract_audio(video_path)
+    transcript = transcribe_audio(audio_path)
+    video_summary = summarize_text(transcript)
+    study_notes = generate_study_notes(video_summary)
+    return transcript, video_summary, study_notes
+
+def ask_question(video_summary, question):
+    return answer_question(question, video_summary)
+
+iface = gr.Blocks()
+with iface:
+    gr.Markdown("# 🎥 Video Summarizer & Study Notes Generator")
+    with gr.Row():
+        video_input = gr.File(label="📂 Upload a video file", type="filepath")
+        transcript_output = gr.Textbox(label="📜 Transcript", lines=5)
+        summary_output = gr.Textbox(label="📄 Video Summary", lines=3)
+        notes_output = gr.Textbox(label="📝 Study Notes", lines=3)
+    
+    process_button = gr.Button("Process Video")
+    process_button.click(process_video, inputs=video_input, outputs=[transcript_output, summary_output, notes_output])
+    
+    question_input = gr.Textbox(label="❓ Ask a question about the video:")
+    answer_output = gr.Textbox(label="💡 Answer")
+    
+    ask_button = gr.Button("Get Answer")
+    ask_button.click(ask_question, inputs=[summary_output, question_input], outputs=answer_output)
+
+iface.launch()