update html

app.py

@@ -358,9 +358,8 @@ title_markdown = ("""
   <div>
     <h1 style="margin: 0;">EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotion</h2>
     <p style="margin: 10px 0;">
-      1. Note that to use the Webcam and Microphone, open <a href="chrome://flags/#unsafely-treat-insecure-origin-as-secure">chrome://flags/#unsafely-treat-insecure-origin-as-secure</a> and put this link into the box.<br/>
-      2. To chat with EMOVA, upload images, enter texts or record audios and then do not forget to <mark>Click 💬 Chat Button</mark> ^v^!<br/>
-      3. Heighten the <code>Max output tokens</code> if necessary to talk longer with EMOVA.
+      1. To chat with EMOVA, upload images, enter texts or record audios and then do not forget to <mark>Click 💬 Chat Button</mark> ^v^!<br/>
+      2. Heighten the <code>Max output tokens</code> if necessary to talk longer with EMOVA.
     </p>
   </div>
 </div>
@@ -404,7 +403,7 @@ def build_demo(embed_mode, cur_dir=None):
     with gr.Blocks(title="EMOVA", theme=gr.themes.Default(), css=block_css) as demo:
         state = gr.State()
         if not embed_mode:
-            gr.Markdown(title_markdown)
+            gr.HTML(title_markdown)
 
         ##############
         # Chatbot

requirements.txt

@@ -10,7 +10,7 @@ timm==0.6.13
 # flash_attn
 https://github.com/Dao-AILab/flash-attention/releases/download/v2.6.3/flash_attn-2.6.3+cu123torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
 scipy
-gradio==4.44.0
+gradio
 
 monotonic_align
 librosa==0.8.0