Update app.py

app.py

@@ -65,8 +65,26 @@ def process_text(uploaded_file):
         )
         summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
 
+        # Post-process the summary
+        words = summary.split()
+        cleaned_summary = []
+        for i, word in enumerate(words):
+            if '-' in word and i < len(words) - 1:
+                word = word.replace('-', '') + words[i + 1]
+                words[i + 1] = ""
+
+            if '.' in word and i != len(words) - 1:
+                word = word.replace('.', '')
+                cleaned_summary.append(word + ' and')
+            else:
+                cleaned_summary.append(word)
+
+        final_summary = ' '.join(cleaned_summary)
+        final_summary = final_summary[0].upper() + final_summary[1:]
+        final_summary = ' '.join(w[0].lower() + w[1:] if w.lower() != 'and' else w for w in final_summary.split())
+
         # Convert summary to speech
-        speech = synthesiser(summary, forward_params={"do_sample": True})
+        speech = synthesiser(final_summary, forward_params={"do_sample": True})
         audio_data = speech["audio"].squeeze()
         normalized_audio_data = np.int16(audio_data / np.max(np.abs(audio_data)) * 32767)
 
@@ -74,7 +92,7 @@ def process_text(uploaded_file):
         output_file = "temp_output.wav"
         scipy.io.wavfile.write(output_file, rate=speech["sampling_rate"], data=normalized_audio_data)
 
-        return summary, output_file
+        return final_summary, output_file
     except Exception as e:
         logging.error(f"Error in summary generation or TTS conversion: {e}")
         return "Error in summary or speech generation", None
@@ -88,4 +106,4 @@ iface = gr.Interface(
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch()