Update app.py

app.py

@@ -8,7 +8,7 @@ from share_btn import community_icon_html, loading_icon_html, share_js
 
 model = whisper.load_model("small")
 wikipedia.set_lang("en")
-passage = wikipedia.summary("platypus", sentences=3)
+passage = wikipedia.summary("pirate code", sentences=2)
 
 
         
@@ -183,7 +183,8 @@ with block:
                 </h1>
               </div>
               <p style="margin-bottom: 10px; font-size: 94%">
-                Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification. This demo cuts audio after around 30 secs.
+                
+                The point of the game is to say the given text as fast as possible without errors. Each error adds a one second penaly to the final time and is measured by the WER metric multiplied by text length. The STT is powered by Whisper, a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification. This demo cuts audio after around 30 secs.
               </p>
             </div>
         """