Update app.py

app.py

@@ -4,25 +4,33 @@ from fpdf import FPDF
 import librosa
 
 def transcribe_and_generate_pdf(audio_file):
-    transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-large")
-    audio, _ = librosa.load(audio_file, sr=16000) 
-    transcription = transcriber(audio)["text"]
+    try:
+        transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-large")
+        audio, _ = librosa.load(audio_file, sr=16000)  # Resample to 16kHz
+        transcription = transcriber(audio)["text"]
 
-    output_pdf = "transcription.pdf"
-    pdf = FPDF()
-    pdf.add_page()
-    pdf.set_font("Arial", size=12)
-    pdf.multi_cell(0, 10, transcription)
-    pdf.output(output_pdf)
-    
-    return transcription, output_pdf
+        output_pdf = "transcription.pdf"
+        pdf = FPDF()
+        pdf.add_page()
+        pdf.set_font("Arial", size=12)
+        pdf.multi_cell(0, 10, transcription)
+        pdf.output(output_pdf)
+
+        return transcription, output_pdf
+
+    except Exception as e:
+        return f"An error occurred: {e}", None
 
 interface = gr.Interface(
     fn=transcribe_and_generate_pdf,
-    inputs=gr.Audio(source="upload", type="filepath"),
-    outputs=[gr.Textbox(label="Transcription"), gr.File(label="Download PDF")],
+    inputs=gr.Audio(type="filepath"),  # Updated to remove 'source' and use 'type="filepath"'
+    outputs=[
+        gr.Textbox(label="Transcription"),
+        gr.File(label="Download PDF")
+    ],
     title="Audio-to-Text and PDF Generator",
+    description="Upload an audio file to get its transcription and download the PDF."
 )
 
 if __name__ == "__main__":
-    interface.launch()
+    interface.launch()