Update app.py

app.py

@@ -18,8 +18,11 @@ pipe = pipeline(
 
 desc = f"""
 This space transcribes Vietnamese words, phrases, and sentences via microphone or audio files then compares the user's text input to what the language model hears.
+
 You will then be given a PASS/FAIL grade to tell you if your spoken audio matches the text you entered.
+
 [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) is the Vietnamese Speech-to-Text model that powers the analysis of the audio files.
+
 """
 
 # Copied from https://github.com/openai/whisper/blob/c09a7ae299c4c34c5839a76380ae407e7d785914/whisper/utils.py#L50