Update app.py

app.py

@@ -41,6 +41,7 @@ def transcribe(audio):
     transcribed_audio = transcribed_audio.replace(".", "")
     transcribed_audio = transcribed_audio.replace("!", "")
     transcribed_audio = transcribed_audio.replace("?", "")
+    transcribed_audio = transcribed_audio.lower()
     
     text_list = transcribed_audio.split(" ")
     
@@ -55,7 +56,7 @@ def transcribe(audio):
         match_ratio =  SequenceMatcher(None, text, correct_answer).ratio()
         
         if match_ratio > 0.8:
-            return f"Partially correct. The answer is {correct_answer}, I heard {text}."
+            return f"Partially correct. The answer is {correct_answer}. I heard {text}."
     # If no match is found.
     return f"Incorrect. The correct answer is {correct_answer}. I heard {transcribed_audio}."
 
@@ -78,7 +79,7 @@ with gr.Blocks(title="Interactive Language Learning") as demo:
         with gr.Column():
             image = gr.Image(value=open_image(),type="pil", interactive=False)
     with gr.Row():
-        answer_box = gr.Text(placeholder="Answer appears here", interactive=False)
+        answer_box = gr.Text(label="Answer appears here", interactive=False)
     with gr.Row():
         with gr.Column():
             process_input = gr.Button("Submit Answer")