update instruction

app.py

@@ -46,7 +46,7 @@ singer_embeddings = {
         "singer8 (female)": "resource/singer/singer_embedding_kising_orange.npy",
         "singer9 (male)": "resource/singer/singer_embedding_m4singer_Tenor-1.npy",
         "singer10 (female)": "resource/singer/singer_embedding_m4singer_Alto-4.npy",
-    }
+    },
 }
 
 model_dict = {
@@ -214,33 +214,38 @@ Music score usually includes lyrics, as well as duration and pitch of each word
     <ol>
         <li><b>Choose Model-Language</b>:
             <ul>
-                <li>"zh" indicates lyrics input in Chinese, and "jp" indicates lyrics input in Japanese.</li>
+                <li>Choose "zh" for Chinese lyrics input or "jp" for Japanese lyrics input.</li>
                 <li>For example, "Model②(Mulitlingual)-zh" means model "Model②(Multilingual)" with lyrics input in Chinese.</li>
             </ul>
         </li>
-        <li><b>[Optional] Choose Singer</b>: Choose one singer you like from the drop-down list.</li>
+        <li><b>[Optional] Choose Singer</b>: Choose a singer from the drop-down menu.</li>
         <li><b>Input lyrics</b>:
             <ul>
-                <li>Lyrics use Chinese characters when the language is 'zh' and hiragana when the language is 'jp'.</li>
-                <li>Special characters such as 'AP' (breath), 'SP' (silence), and '-' (slur, only for Chinese lyrics) can also be used.</li>
-                <li>Lyrics sequence should be separated by either a space (' ') or a newline ('\\n'), without the quotation marks.</li>
+                <li>Input Chinese characters for "zh" and hiragana for "jp".</li>
+                <li>You may include special symbols: 'AP' for breath, 'SP' for silence, and '-' for slur (Chinese lyrics only).</li>
+                <li>Separate each lyric by either a space (' ') or a newline ('\\n') (no quotation marks needed).</li>
             </ul>
         </li>
         <li><b>Input durations</b>:
             <ul>
-                <li>Durations use float number as input.</li>
-                <li>Length of duration sequence should <b>be same as lyric sequence</b>, with each duration corresponding to the respective lyric.</li>
-                <li>Durations sequence should be separated by either a space (' ') or a newline ('\\n'), without the quotation marks.</li>
+                <li>Input durations as float numbers.</li>
+                <li>The durations sequence should <b>match the lyric sequence in length</b>, with each duration aligned to a lyric.</li>
+                <li>Separate each duration by a space (' ') or a newline ('\\n') (no quotation marks needed).</li>
             </ul>
         </li>
         <li><b>Input pitches</b>:
             <ul>
-                <li>Pitches use MIDI note or MIDI note number as input. Specially, "69" in MIDI note number represents "A4" in MIDI note.</li>
-                <li>Length of pitch sequence should <b>be same as lyric sequence</b>, with each pitch corresponding to the respective lyric.</li>
-                <li>Pitches sequence should be separated by either a space (' ') or a newline ('\\n'), without the quotation marks.</li>
+                <li>Input MIDI note names or MIDI note numbers (e.g., MIDI note name "69" represents the MIDI note number "A4", and others follow accordingly).</li>
+                <li>The pitch sequence should <b>match the lyric sequence in length</b>, with each pitch corresponding to a lyric.</li>
+                <li>Separate each duration by a space (' ') or a newline ('\\n') (no quotation marks needed).</li>
+            </ul>
+        </li>
+        <li><b>Hit "Generate" and listen</b>:
+            <ul>
+                <li>"Running Status" shows the status of singing generatation. If any error exists, it will show the error information.</li>
+                <li>"Pseudo MOS" represents predicted mean opinion score for the generated song.</li>
             </ul>
         </li>
-        <li><b>Hit "Generate" and listen to the result!</b></li>
     </ol>
 </div>