Update app.py

app.py

@@ -1,24 +1,28 @@
-import streamlit as st
 import os
+import streamlit as st
 import moviepy.editor as mp
 import whisper
 from transformers import pipeline
 
-# Function to extract audio from video
+# ✅ Ensure ffmpeg is installed (needed for moviepy)
+if not os.path.exists("/usr/bin/ffmpeg"):
+    os.system("apt-get update && apt-get install -y ffmpeg")
+
+# ✅ Function to extract audio from a video
 def extract_audio(video_path, audio_path="audio.wav"):
     if os.path.exists(audio_path):
         os.remove(audio_path)
-    video = mp.VideoFileClip(video_path)
+    video = mp.VideoFileClip(video_path)  # Use mp.VideoFileClip
     video.audio.write_audiofile(audio_path)
     return audio_path
 
-# Function to transcribe audio using Whisper
+# ✅ Function to transcribe audio using Whisper
 def transcribe_audio(audio_path):
-    model = whisper.load_model("base")
+    model = whisper.load_model("base", download_root="./models")  # Ensure model is downloaded
     result = model.transcribe(audio_path)
     return result["text"]
 
-# Function to summarize text
+# ✅ Function to summarize text
 def summarize_text(text):
     summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
     max_chunk_size = 1000
@@ -26,22 +30,23 @@ def summarize_text(text):
     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
+# ✅ 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
+# ✅ Function to answer user 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
+# ✅ Streamlit UI
 st.title("Lecture Video Processor 🎥📝")
 
+# File uploader
 uploaded_file = st.file_uploader("📤 Upload a video file", type=["mp4", "mov", "avi", "mkv"])
 
 if uploaded_file:
@@ -51,22 +56,27 @@ if uploaded_file:
 
     st.success("✅ Video uploaded successfully!")
 
+    # Extract audio
     st.info("🔊 Extracting audio...")
     audio_path = extract_audio(video_path)
     st.success("✅ Audio extracted!")
 
+    # Transcribe audio
     st.info("🎙️ Transcribing audio...")
     transcript = transcribe_audio(audio_path)
     st.text_area("📜 Transcript", transcript, height=200)
 
+    # Summarize transcript
     st.info("📄 Summarizing transcript...")
     video_summary = summarize_text(transcript)
     st.text_area("📌 Summary", video_summary, height=150)
 
+    # Generate study notes
     st.info("📝 Generating study notes...")
     study_notes = generate_study_notes(video_summary)
     st.text_area("📖 Study Notes", study_notes, height=150)
 
+    # Q&A Section
     question = st.text_input("❓ Ask a question about the video:")
     if question:
         answer = answer_question(question, video_summary)