Update templates/index.html

templates/index.html

@@ -75,12 +75,11 @@
 
         <div id="evaluation-info" class="mb-5">
             <p class="text-start">
-                <span class="section-title"><i class="fas fa-info-circle"></i>Welcome!</span>
-                <strong>Welcome to the Speech-to-Speech (S2S) Model Evaluation! 🎤</strong>
+                <span class="section-title"><i class="fas fa-info-circle"></i>Welcome to the Speech-to-Speech (S2S) Model Evaluation! 🎤</span>
                 <br><br>
                 In this evaluation, you will assess the performance of 4 S2S models:
-                <strong>ChatGPT-4o</strong> 🤖, <strong>FunAudioLLM</strong> 🎧, <strong>SpeechGPT</strong> 🗣️, and
-                <strong>Mini-Omni</strong> 🌟.
+                <strong>ChatGPT-4o</strong>, <strong>FunAudioLLM</strong>, <strong>SpeechGPT</strong>, and
+                <strong>Mini-Omni</strong>.
                 The goal is to evaluate how well these models handle various speech tasks across different domains.
                 <br><br>
                 <span class="section-title"><i class="fas fa-tasks"></i>How It Works</span>
@@ -89,8 +88,9 @@
                 For example:
                 <br><br>
 
-                <strong>Audio Sample:</strong>
-                <audio controls>
+                <span style="vertical-align: middle; line-height: 1.2; display: inline-block;"><strong>Audio
+                        Sample:</strong></span>
+                <audio controls style="vertical-align: middle;">
                     <source src="/static/audio/sample/input_audio.wav" type="audio/wav">
                 </audio>
 
@@ -108,7 +108,7 @@
 
                 <!-- ChatGPT-4o Output -->
                 <span><strong>ChatGPT-4o:</strong></span>
-                <audio controls>
+                <audio controls style="vertical-align: middle;">
                     <source src="/static/audio/sample/4o_audio.wav" type="audio/wav">
                 </audio>
                 <p class="text-start" style="margin-left: 20px;">
@@ -117,7 +117,7 @@
 
                 <!-- FunAudioLLM Output -->
                 <span><strong>FunAudioLLM:</strong></span>
-                <audio controls>
+                <audio controls style="vertical-align: middle;">
                     <source src="/static/audio/sample/FunAudio_audio.wav" type="audio/wav">
                 </audio>
                 <p class="text-start" style="margin-left: 20px;">
@@ -126,7 +126,7 @@
 
                 <!-- SpeechGPT Output -->
                 <span><strong>SpeechGPT:</strong></span>
-                <audio controls>
+                <audio controls style="vertical-align: middle;">
                     <source src="/static/audio/sample/SpeechGPT.wav" type="audio/wav">
                 </audio>
                 <p class="text-start" style="margin-left: 20px;">
@@ -135,7 +135,7 @@
 
                 <!-- Mini-Omni Output -->
                 <span><strong>Mini-Omni:</strong></span>
-                <audio controls>
+                <audio controls style="vertical-align: middle;">
                     <source src="/static/audio/sample/mini-omni.wav" type="audio/wav">
                 </audio>
                 <p class="text-start" style="margin-left: 20px;">