Update app.py

app.py

@@ -1,19 +1,15 @@
 import gradio as gr
-import os
 from transformers import pipeline
 from langdetect import detect
 
-def process_audio(audio_file):
+def process_audio(audio_path):
     try:
-        # audio_file is a tuple (file_obj, file_path)
-        audio_path = audio_file if isinstance(audio_file, str) else audio_file.name
-
-        # Transcribe
+        # Transcription
         asr = pipeline("automatic-speech-recognition", model="openai/whisper-large")
         result = asr(audio_path)
         transcript = result["text"]
     except Exception as e:
-        return "Error in transcription: " + str(e), "", "", ""
+        return f"Error in transcription: {e}", "", "", ""
     try:
         detected_lang = detect(transcript)
     except Exception:
@@ -38,10 +34,20 @@ def process_audio(audio_file):
         summary_text = summary[0]["summary_text"]
     except Exception as e:
         summary_text = f"Error summarizing: {e}"
-    # 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("## Audio Transcript, Translation & Summary (Powered by Whisper + Hugging Face)")
+    gr.Markdown("## Audio Transcript, Translation & Summary (Whisper + Hugging Face)")
     audio_input = gr.Audio(source="upload", type="filepath", label="Upload MP3/WAV Audio")
-    btn = gr
+    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_audio,
+        inputs=[audio_input],
+        outputs=[lang_out, transcript_out, transcript_en_out, summary_out]
+    )
+
+demo.launch()