Update app.py

app.py

@@ -1,26 +1,14 @@
 import gradio as gr
 import os
-import subprocess
 from transformers import pipeline
 from langdetect import detect
 
-def download_audio(youtube_url):
-    output_file = "audio.mp3"
-    # Remove old file if exists
-    if os.path.exists(output_file):
-        os.remove(output_file)
-    cmd = [
-        "yt-dlp", "-x", "--audio-format", "mp3", "-o", output_file, youtube_url
-    ]
-    subprocess.run(cmd, check=True)
-    return output_file
-
-def process_youtube(youtube_url):
-    try:
-        audio_path = download_audio(youtube_url)
-    except Exception as e:
-        return "Error downloading audio: " + str(e), "", "", ""
+def process_audio(audio_file):
     try:
+        # audio_file is a tuple (file_obj, file_path)
+        audio_path = audio_file if isinstance(audio_file, str) else audio_file.name
+
+        # Transcribe
         asr = pipeline("automatic-speech-recognition", model="openai/whisper-large")
         result = asr(audio_path)
         transcript = result["text"]
@@ -50,22 +38,10 @@ def process_youtube(youtube_url):
         summary_text = summary[0]["summary_text"]
     except Exception as e:
         summary_text = f"Error summarizing: {e}"
-    if os.path.exists(audio_path):
-        os.remove(audio_path)
+    # Optionally, remove uploaded file if it's saved on disk
     return lang_text, transcript, transcript_en, summary_text
 
 with gr.Blocks() as demo:
-    gr.Markdown("## YouTube Transcript, Translation & Summary (Powered by Whisper + Hugging Face)")
-    url_input = gr.Textbox(label="YouTube URL")
-    btn = gr.Button("Process")
-    lang_out = gr.Textbox(label="Detected Language")
-    transcript_out = gr.Textbox(label="Original Transcript")
-    transcript_en_out = gr.Textbox(label="English Transcript (if translated)")
-    summary_out = gr.Textbox(label="Summary")
-    btn.click(
-        process_youtube,
-        inputs=[url_input],
-        outputs=[lang_out, transcript_out, transcript_en_out, summary_out]
-    )
-
-demo.launch()
+    gr.Markdown("## Audio Transcript, Translation & Summary (Powered by Whisper + Hugging Face)")
+    audio_input = gr.Audio(source="upload", type="filepath", label="Upload MP3/WAV Audio")
+    btn = gr