Update app.py

app.py

@@ -1,85 +1,70 @@
-# app.py
 import streamlit as st
+import os
 from moviepy.editor import VideoFileClip
 import whisper
 from transformers import pipeline
-import os
-
-# Set page title and layout
-st.set_page_config(page_title="Video Summarizer", layout="wide")
-
-# Title
-st.title("Video Summarizer 🎥📝")
-st.write("Upload a video, and get a transcript, summary, study notes, and answers to your questions!")
 
-# Step 1: Upload Video
-uploaded_file = st.file_uploader("Upload a video file", type=["mp4", "avi", "mov"])
-if uploaded_file is not None:
-    # Save the uploaded video to a temporary file
-    video_path = "uploaded_video.mp4"
-    with open(video_path, "wb") as f:
-        f.write(uploaded_file.getbuffer())
-    st.success("Video uploaded successfully!")
-
-    # Step 2: Extract Audio
-    st.header("Step 1: Extract Audio")
-    audio_path = "audio.wav"
+# 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)
-    st.audio(audio_path, format="audio/wav")
-    st.success("Audio extracted successfully!")
+    return audio_path
+
+# Function to transcribe audio using Whisper
+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 = [summarizer(chunk, max_length=130, min_length=30, do_sample=False)[0]["summary_text"] for chunk in chunks]
+    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"]
+
+# Streamlit App
+st.title("Lecture Video Processor")
+
+uploaded_file = st.file_uploader("Upload a video file", type=["mp4", "mov", "avi", "mkv"])
+
+if uploaded_file:
+    video_path = uploaded_file.name
+    with open(video_path, "wb") as f:
+        f.write(uploaded_file.read())
+
+    st.info("Extracting audio...")
+    audio_path = extract_audio(video_path)
 
-    # Step 3: Transcribe Audio
-    st.header("Step 2: Transcribe Audio")
-    if st.button("Transcribe Audio"):
-        with st.spinner("Transcribing audio..."):
-            model = whisper.load_model("base")
-            result = model.transcribe(audio_path)
-            transcript = result["text"]
-            st.text_area("Transcript", transcript, height=200)
-            st.success("Transcription complete!")
+    st.info("Transcribing audio...")
+    transcript = transcribe_audio(audio_path)
+    st.text_area("Transcript", transcript, height=200)
 
-    # Step 4: Summarize Transcript
-    st.header("Step 3: Summarize Transcript")
-    if st.button("Summarize Transcript"):
-        with st.spinner("Summarizing transcript..."):
-            summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
-            max_chunk_size = 1000
-            chunks = [transcript[i:i + max_chunk_size] for i in range(0, len(transcript), 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"])
-            video_summary = " ".join(summaries)
-            st.text_area("Summary", video_summary, height=200)
-            st.success("Summarization complete!")
+    st.info("Summarizing transcript...")
+    video_summary = summarize_text(transcript)
+    st.text_area("Summary", video_summary, height=150)
 
-    # Step 5: Generate Study Notes
-    st.header("Step 4: Generate Study Notes")
-    if st.button("Generate Study Notes"):
-        with st.spinner("Generating study notes..."):
-            generator = pipeline("text-generation", model="gpt2")
-            prompt = f"Create study notes from the following summary:\n{video_summary}"
-            study_notes = generator(
-                prompt,
-                max_length=400,
-                max_new_tokens=200,
-                num_return_sequences=1,
-                truncation=True
-            )
-            st.text_area("Study Notes", study_notes[0]["generated_text"], height=200)
-            st.success("Study notes generated!")
+    st.info("Generating study notes...")
+    study_notes = generate_study_notes(video_summary)
+    st.text_area("Study Notes", study_notes, height=150)
 
-    # Step 6: Question Answering
-    st.header("Step 5: Ask a Question")
-    question = st.text_input("Enter your question:")
-    if st.button("Get Answer"):
-        with st.spinner("Finding answer..."):
-            qa_pipeline = pipeline("question-answering", model="distilbert-base-uncased-distilled-squad")
-            answer = qa_pipeline(question=question, context=video_summary)
-            st.text_area("Answer", answer["answer"], height=100)
-            st.success("Answer found!")
-else:
-    st.warning("Please upload a video file to get started.")
+    question = st.text_input("Ask a question about the video:")
+    if question:
+        answer = answer_question(question, video_summary)
+        st.write("Answer:", answer)