Spaces:
Running
Running
Update templates/index.html
Browse files- 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>
|