Update README.md

README.md

@@ -47,7 +47,7 @@ Most TTS models require a fixed number of steps to produce one second of audio (
   </tr>
   <tr>
     <td><img src="final-graphics-polished/real-time.png" alt="Speed" height="200px"></td>
-    <td><img src="final-graphics-polished/speaker-sim.png" alt="Speaker Similarity" height="200px"></td>
+    <td><img src="final-graphics-polished/naturalness.png" alt="Speaker Similarity" height="200px"></td>
   </tr>
 </table>