Create app.py

app.py

@@ -0,0 +1,141 @@
+# Install necessary libraries if running in a fresh environment
+# pip install streamlit gradio openai-whisper youtube-dl moviepy pydub transformers sentencepiece langchain python-magic pillow ffmpeg tqdm pyannote.audio
+
+import os
+import streamlit as st
+from pytube import YouTube
+from moviepy.video.io.VideoFileClip import VideoFileClip
+from pydub import AudioSegment
+import whisper
+from transformers import pipeline, MarianMTModel, MarianTokenizer
+
+
+# App Configuration
+st.set_page_config(page_title="Video-to-Text Summarizer", layout="centered")
+
+# Welcome Page
+st.title("🎥 Video-to-Text Summarization App")
+st.markdown("""
+This app helps you:
+- Convert videos into text and summarize them.
+- Extract multilingual transcriptions and translations.
+- Process videos with multiple speakers.
+
+Navigate using the sidebar!
+""")
+
+# Sidebar for Navigation
+st.sidebar.header("Navigation")
+nav_option = st.sidebar.radio("Go to", ["Welcome", "Upload Video", "Process Video", "Results"])
+
+# Global Variables
+video_path = None
+audio_path = None
+transcription = None
+summary = None
+translated_summary = None
+
+
+# Upload Video Section
+if nav_option == "Upload Video":
+    st.header("Upload Your Video")
+    upload_option = st.selectbox("Select Upload Method", ["Local", "YouTube URL"])
+
+    if upload_option == "Local":
+        video_file = st.file_uploader("Upload your video file", type=["mp4", "mkv", "avi"])
+        if video_file:
+            with open("uploaded_video.mp4", "wb") as f:
+                f.write(video_file.read())
+            video_path = "uploaded_video.mp4"
+            st.success("Video uploaded successfully!")
+
+    elif upload_option == "YouTube URL":
+        youtube_url = st.text_input("Enter YouTube URL")
+        if youtube_url:
+            os.system(f"yt-dlp -o video.mp4 {youtube_url}")
+            video_path = "video.mp4"
+            st.success("YouTube video downloaded successfully!")
+
+# Process Video Section
+if nav_option == "Process Video" and video_path:
+    st.header("Process Your Video")
+
+    # Video Chunking
+    def chunk_video(video_path, chunk_duration=300):
+        try:
+            video = VideoFileClip(video_path)
+            total_duration = int(video.duration)
+            for start in range(0, total_duration, chunk_duration):
+                end = min(start + chunk_duration, total_duration)
+                chunk = video.subclip(start, end)
+                chunk.write_videofile(f"chunk_{start}-{end}.mp4")
+            st.success("Video chunked successfully!")
+        except Exception as e:
+            st.error(f"Error in chunking video: {str(e)}")
+
+    # Audio Extraction
+    def extract_audio(video_path):
+        try:
+            audio = AudioSegment.from_file(video_path)
+            audio.export("extracted_audio.mp3", format="mp3")
+            st.success("Audio extracted successfully!")
+            return "extracted_audio.mp3"
+        except Exception as e:
+            st.error(f"Error in extracting audio: {str(e)}")
+            return None
+
+    st.write("Processing your video...")
+    audio_path = extract_audio(video_path)
+
+    # Transcription
+    def transcribe_audio(audio_path):
+        try:
+            model = whisper.load_model("base")
+            result = model.transcribe(audio_path)
+            st.text_area("Transcription", result['text'], height=200)
+            return result['text']
+        except Exception as e:
+            st.error(f"Error in transcription: {str(e)}")
+            return None
+
+    if audio_path:
+        transcription = transcribe_audio(audio_path)
+
+# Summarization Section
+if nav_option == "Results" and transcription:
+    st.header("Results")
+
+    # Summarization
+    def summarize_text(text):
+        try:
+            summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+            summary = summarizer(text, max_length=150, min_length=30, do_sample=False)
+            st.text_area("Summary", summary[0]['summary_text'], height=150)
+            return summary[0]['summary_text']
+        except Exception as e:
+            st.error(f"Error in summarization: {str(e)}")
+            return None
+
+    summary = summarize_text(transcription)
+
+    # Translation
+    def translate_text(text, src_lang="en", tgt_lang="es"):
+        try:
+            model_name = f"Helsinki-NLP/opus-mt-{src_lang}-{tgt_lang}"
+            tokenizer = MarianTokenizer.from_pretrained(model_name)
+            model = MarianMTModel.from_pretrained(model_name)
+            translated = model.generate(**tokenizer(text, return_tensors="pt", padding=True))
+            translated_text = tokenizer.decode(translated[0], skip_special_tokens=True)
+            st.text_area("Translated Summary", translated_text, height=150)
+            return translated_text
+        except Exception as e:
+            st.error(f"Error in translation: {str(e)}")
+            return None
+
+    target_language = st.selectbox("Select Translation Language", ["es", "fr", "de", "zh"])
+    if target_language:
+        translated_summary = translate_text(summary, tgt_lang=target_language)
+
+# Error Notifications
+if nav_option in ["Process Video", "Results"] and not video_path:
+    st.error("Please upload a video to proceed.")