KurtDu commited on
Commit
ca332d0
·
verified ·
1 Parent(s): fbe556d

Update templates/index.html

Browse files
Files changed (1) hide show
  1. templates/index.html +0 -8
templates/index.html CHANGED
@@ -76,35 +76,27 @@
76
  <div id="evaluation-info" class="mb-5">
77
  <p class="text-start">
78
  <span class="section-title"><i class="fas fa-info-circle"></i>Welcome to the Speech-to-Speech (S2S) Model Evaluation! 🎤</span>
79
- <br><br>
80
  In this evaluation, you will assess the performance of 4 S2S models:
81
  <strong>ChatGPT-4o</strong>, <strong>FunAudioLLM</strong>, <strong>SpeechGPT</strong>, and
82
  <strong>Mini-Omni</strong>.
83
  The goal is to evaluate how well these models handle various speech tasks across different domains.
84
- <br><br>
85
  <span class="section-title"><i class="fas fa-tasks"></i>How It Works</span>
86
  Once you select a specific domain and task (e.g., <em>Educational Tutoring</em> and <em>Rhythm Control</em>),
87
  you will proceed to the evaluation stage. In each round, you will be presented with an audio input. 🎵
88
  For example:
89
- <br><br>
90
-
91
  <span style="vertical-align: middle; line-height: 1.2; display: inline-block;"><strong>Audio
92
  Sample:</strong></span>
93
  <audio controls style="vertical-align: middle;">
94
  <source src="/static/audio/sample/input_audio.wav" type="audio/wav">
95
  </audio>
96
-
97
- <br><br>
98
  The corresponding text is:
99
  <em>"Say the following sentence at my speed first, then say it again very slowly:
100
  'Artificial intelligence is changing the world in many ways.'" </em> 🧠
101
  <small>(Note: the audio plays at 1.5x the normal speed.)</small>
102
- <br><br>
103
 
104
  <span class="section-title"><i class="fas fa-star"></i>Model Responses</span>
105
  The responses of different S2S models will be provided, and your task is to choose which response best follows
106
  the instructions. For example:
107
- <br><br>
108
 
109
  <!-- ChatGPT-4o Output -->
110
  <span><strong>ChatGPT-4o:</strong></span>
 
76
  <div id="evaluation-info" class="mb-5">
77
  <p class="text-start">
78
  <span class="section-title"><i class="fas fa-info-circle"></i>Welcome to the Speech-to-Speech (S2S) Model Evaluation! 🎤</span>
 
79
  In this evaluation, you will assess the performance of 4 S2S models:
80
  <strong>ChatGPT-4o</strong>, <strong>FunAudioLLM</strong>, <strong>SpeechGPT</strong>, and
81
  <strong>Mini-Omni</strong>.
82
  The goal is to evaluate how well these models handle various speech tasks across different domains.
 
83
  <span class="section-title"><i class="fas fa-tasks"></i>How It Works</span>
84
  Once you select a specific domain and task (e.g., <em>Educational Tutoring</em> and <em>Rhythm Control</em>),
85
  you will proceed to the evaluation stage. In each round, you will be presented with an audio input. 🎵
86
  For example:
 
 
87
  <span style="vertical-align: middle; line-height: 1.2; display: inline-block;"><strong>Audio
88
  Sample:</strong></span>
89
  <audio controls style="vertical-align: middle;">
90
  <source src="/static/audio/sample/input_audio.wav" type="audio/wav">
91
  </audio>
 
 
92
  The corresponding text is:
93
  <em>"Say the following sentence at my speed first, then say it again very slowly:
94
  'Artificial intelligence is changing the world in many ways.'" </em> 🧠
95
  <small>(Note: the audio plays at 1.5x the normal speed.)</small>
 
96
 
97
  <span class="section-title"><i class="fas fa-star"></i>Model Responses</span>
98
  The responses of different S2S models will be provided, and your task is to choose which response best follows
99
  the instructions. For example:
 
100
 
101
  <!-- ChatGPT-4o Output -->
102
  <span><strong>ChatGPT-4o:</strong></span>