Update app.py

app.py

@@ -1,50 +1,53 @@
 import gradio as gr
+import torch
 import os
+import subprocess
+from pytubefix import YouTube
+from moviepy.editor import VideoFileClip
 from transformers import pipeline
 
-# Load ASR (Speech-to-Text) pipeline with timestamp handling
-asr = pipeline(task="automatic-speech-recognition", model="distil-whisper/distil-small.en")
+# Ensure required packages are installed inside Hugging Face Spaces
+subprocess.run(["pip", "install", "pytubefix", "moviepy", "transformers", "torchaudio"], check=True)
+
+# Load Whisper model for transcription
+asr = pipeline("automatic-speech-recognition", model="distil-whisper/distil-small.en")
 
 # Load Summarization model
 summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
 
-# Function to transcribe and summarize audio
-def transcribe_and_summarize(audio_file):
-    if audio_file is None:
-        return "Error: No audio file provided.", ""
 
+def process_youtube_link(youtube_url):
     try:
-        # Transcribe audio (handling long-form audio)
-        transcription_result = asr(audio_file, return_timestamps=True)
-        
-        # Extract transcribed text
-        transcribed_text = " ".join([segment['text'] for segment in transcription_result['chunks']])
-
-        # Ensure the transcribed text isn't too short for summarization
-        if len(transcribed_text.split()) < 50:
-            summarized_text = "Text too short to summarize."
-        else:
-            # Summarize the transcribed text
-            summary_result = summarizer(transcribed_text, max_length=100, min_length=30, do_sample=False)
-            summarized_text = summary_result[0]['summary_text']
-
-        return transcribed_text, summarized_text
+        # Download YouTube Video
+        yt = YouTube(youtube_url)
+        video_stream = yt.streams.filter(only_audio=True).first()
+        video_path = video_stream.download(filename="video.mp4")
+
+        # Extract Audio
+        audio_path = "audio.wav"
+        video = VideoFileClip(video_path)
+        video.audio.write_audiofile(audio_path)
+
+        # Transcribe Audio
+        transcription = asr(audio_path)
+        transcribed_text = transcription["text"]
+
+        # Summarize Transcription
+        summary = summarizer(transcribed_text, max_length=150, min_length=50, do_sample=False)[0]["summary_text"]
+
+        return transcribed_text, summary
 
     except Exception as e:
         return f"Error: {str(e)}", ""
 
-# Create Gradio interface
+
+# Create Gradio Interface
 iface = gr.Interface(
-    fn=transcribe_and_summarize,
-    inputs=gr.Audio(type="filepath"),  # Accepts an audio file
-    outputs=[
-        gr.Textbox(label="Transcribed Text"),  
-        gr.Textbox(label="Summarized Text")
-    ]
+    fn=process_youtube_link,
+    inputs=gr.Textbox(label="Enter YouTube URL"),
+    outputs=[gr.Textbox(label="Transcription"), gr.Textbox(label="Summary")],
+    title="YouTube Video Transcriber & Summarizer",
+    description="Enter a YouTube link, and this app will transcribe and summarize the audio.",
 )
 
-# Get port safely (default to 7860 if not set)
-port = int(os.environ.get('PORT1', 7860))
-
-# Launch Gradio app
-iface.launch(share=True, server_port=port)
+iface.launch()