refactor: update tab labels and button texts for clarity in speaker selection steps

app.py

@@ -216,12 +216,12 @@ with demo:
         elem_id="head-html-block",
     )
 
-    with gr.Tab("預設語者"):
+    with gr.Tab("預設配音員"):
         with gr.Row():
             with gr.Column():
                 default_speaker_language = gr.Dropdown(
                     choices=g2p_object.keys(),
-                    label="選擇語言",
+                    label="步驟一：選擇語言",
                     value="阿美_秀姑巒",
                 )
 
@@ -230,26 +230,28 @@ with demo:
 
                 default_speaker_refs = gr.Dropdown(
                     choices=get_refs_by_language(default_speaker_language.value),
-                    label="選擇配音員",
+                    label="步驟二：選擇配音員",
                     value=get_refs_by_language(default_speaker_language.value)[0],
                 )
 
                 default_speaker_gen_text_input = gr.Textbox(
-                    label="輸入文字（上限 300 字元）",
+                    label="步驟三：輸入文字（上限 300 字元）",
                     value="",
                 )
 
-                default_speaker_generate_btn = gr.Button("開始合成", variant="primary")
+                default_speaker_generate_btn = gr.Button(
+                    "步驟四：開始合成", variant="primary"
+                )
 
             with gr.Column():
                 default_speaker_audio_output = gr.Audio(label="合成結果")
 
-    with gr.Tab("自定義語者"):
+    with gr.Tab("自己當配音員"):
         with gr.Row():
             with gr.Column():
                 custom_speaker_language = gr.Dropdown(
                     choices=g2p_object.keys(),
-                    label="選擇語言",
+                    label="步驟一：選擇語言",
                     value="阿美_秀姑巒",
                 )
 
@@ -257,7 +259,7 @@ with demo:
                     value=refs_config.get(f"{custom_speaker_language.value}_1", {}).get(
                         "text", ""
                     ),
-                    label="錄製下方句子或上傳與句子相符的音檔",
+                    label="步驟二：點選🎙️錄製下方句子，或上傳與句子相符的音檔",
                 )
 
                 custom_speaker_audio_input = gr.Audio(
@@ -269,11 +271,13 @@ with demo:
                 )
 
                 custom_speaker_gen_text_input = gr.Textbox(
-                    label="輸入合成文字（上限 300 字元）",
+                    label="步驟三：輸入合成文字（上限 300 字元）",
                     value="",
                 )
 
-                custom_speaker_generate_btn = gr.Button("開始合成", variant="primary")
+                custom_speaker_generate_btn = gr.Button(
+                    "步驟四：開始合成", variant="primary"
+                )
 
             with gr.Column():
                 custom_speaker_audio_output = gr.Audio(label="合成結果")