app.py

# app.py
import gradio as gr
from moviepy.editor import VideoFileClip
import whisper
from transformers import pipeline
import os

# Function to extract audio from video
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)
    return audio_path

# Function to transcribe audio
def transcribe_audio(audio_path):
    model = whisper.load_model("base")
    result = model.transcribe(audio_path)
    return result["text"]

# Function to summarize text
def summarize_text(text):
    summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
    max_chunk_size = 1000
    chunks = [text[i:i + max_chunk_size] for i in range(0, len(text), max_chunk_size)]
    summaries = []
    for chunk in chunks:
        summary = summarizer(chunk, max_length=130, min_length=30, do_sample=False)
        summaries.append(summary[0]["summary_text"])
    return " ".join(summaries)

# Function to generate study notes
def generate_study_notes(summary):
    generator = pipeline("text-generation", model="gpt2")
    prompt = f"Create study notes from the following summary:\n{summary}"
    study_notes = generator(
        prompt,
        max_length=400,
        max_new_tokens=200,
        num_return_sequences=1,
        truncation=True
    )
    return study_notes[0]["generated_text"]

# Function to answer questions
def answer_question(question, context):
    qa_pipeline = pipeline("question-answering", model="distilbert-base-uncased-distilled-squad")
    result = qa_pipeline(question=question, context=context)
    return result["answer"]

# Main function to process video
def process_video(video_file):
    # Step 1: Save the uploaded video
    video_path = "uploaded_video.mp4"
    with open(video_path, "wb") as f:
        f.write(video_file)
    
    # Step 2: Extract audio
    audio_path = extract_audio(video_path)
    
    # Step 3: Transcribe audio
    transcript = transcribe_audio(audio_path)
    
    # Step 4: Summarize transcript
    summary = summarize_text(transcript)
    
    # Step 5: Generate study notes
    study_notes = generate_study_notes(summary)
    
    return transcript, summary, study_notes

# Gradio interface
def gradio_interface(video_file, question):
    # Process the video
    transcript, summary, study_notes = process_video(video_file)
    
    # Answer the question
    if question.strip():
        answer = answer_question(question, summary)
    else:
        answer = "Please enter a question."
    
    return transcript, summary, study_notes, answer

# Create Gradio app
iface = gr.Interface(
    fn=gradio_interface,
    inputs=[
        gr.Video(label="Upload Video"),
        gr.Textbox(label="Ask a Question (Optional)")
    ],
    outputs=[
        gr.Textbox(label="Transcript"),
        gr.Textbox(label="Summary"),
        gr.Textbox(label="Study Notes"),
        gr.Textbox(label="Answer")
    ],
    title="Video Summarizer 🎥📝",
    description="Upload a video, and get a transcript, summary, study notes, and answers to your questions!"
)

# Launch the app
iface.launch()