Spaces:
Sleeping
Sleeping
Update templates/index.html
Browse files- templates/index.html +82 -51
templates/index.html
CHANGED
|
@@ -72,17 +72,24 @@
|
|
| 72 |
margin-right: 10px;
|
| 73 |
}
|
| 74 |
|
| 75 |
-
audio {
|
| 76 |
-
margin-top: 10px;
|
| 77 |
-
margin-bottom: 15px;
|
| 78 |
-
}
|
| 79 |
-
|
| 80 |
.audio-container {
|
| 81 |
text-align: center;
|
| 82 |
margin-top: 20px;
|
| 83 |
}
|
| 84 |
|
| 85 |
-
.audio-container audio {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
display: inline-block;
|
| 87 |
}
|
| 88 |
</style>
|
|
@@ -94,86 +101,110 @@
|
|
| 94 |
|
| 95 |
<div id="evaluation-info" class="mb-5">
|
| 96 |
<p class="text-start">
|
| 97 |
-
<span class="section-title"><i class="fas fa-info-circle"></i>Welcome to the Speech-to-Speech (S2S)
|
|
|
|
| 98 |
In this evaluation, you will assess the performance of 4 S2S models:
|
| 99 |
<strong>ChatGPT-4o</strong>, <strong>FunAudioLLM</strong>, <strong>SpeechGPT</strong>, and
|
| 100 |
<strong>Mini-Omni</strong>.
|
| 101 |
The goal is to evaluate how well these models handle various speech tasks across different domains.
|
| 102 |
<span class="section-title"><i class="fas fa-tasks"></i>How It Works</span>
|
| 103 |
-
Once you select a specific domain and task (e.g., <em>Educational Tutoring</em> and <em>Rhythm
|
|
|
|
| 104 |
you will proceed to the evaluation stage. In each round, you will be presented with an audio input. 🎵
|
| 105 |
For example:
|
| 106 |
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
<
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
|
|
|
|
|
|
| 117 |
|
| 118 |
-
|
| 119 |
|
| 120 |
-
|
| 121 |
-
|
|
|
|
| 122 |
<audio controls>
|
| 123 |
<source src="/static/audio/sample/4o_audio.wav" type="audio/wav">
|
| 124 |
</audio>
|
| 125 |
-
<p>
|
| 126 |
-
<strong>Performance:</strong> 🎙️ Speech: Partially followed the instruction on speed. 🧾
|
| 127 |
-
Semantics: Accurately followed the instruction, with no semantic deviation or missing
|
| 128 |
-
information.
|
| 129 |
-
</p>
|
| 130 |
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
|
| 132 |
-
<div class="audio-
|
| 133 |
-
<span
|
| 134 |
<audio controls>
|
| 135 |
<source src="/static/audio/sample/FunAudio_audio.wav" type="audio/wav">
|
| 136 |
</audio>
|
| 137 |
-
<p>
|
| 138 |
-
<strong>Performance:</strong> 🎙️ Speech: Partially followed the instruction on speed. 🧾
|
| 139 |
-
Semantics: Accurately followed the instruction, with no semantic deviation or missing
|
| 140 |
-
information.
|
| 141 |
-
</p>
|
| 142 |
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 143 |
|
| 144 |
-
<div class="audio-
|
| 145 |
-
<span
|
| 146 |
<audio controls>
|
| 147 |
<source src="/static/audio/sample/SpeechGPT.wav" type="audio/wav">
|
| 148 |
</audio>
|
| 149 |
-
<p>
|
| 150 |
-
<strong>Performance:</strong> 🎙️ Speech: Did not follow the instruction on speed. 🧾 Semantics:
|
| 151 |
-
Partially followed the instruction, with minor semantic deviation and missing information.
|
| 152 |
-
</p>
|
| 153 |
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 154 |
|
| 155 |
-
<
|
| 156 |
-
|
|
|
|
|
|
|
| 157 |
<audio controls>
|
| 158 |
<source src="/static/audio/sample/mini-omni.wav" type="audio/wav">
|
| 159 |
</audio>
|
| 160 |
-
<p>
|
| 161 |
-
<strong>Performance:</strong> 🎙️ Speech: Did not follow the instruction on speed. 🧾 Semantics:
|
| 162 |
-
Did not follow the instruction, with significant semantic deviation and missing information.
|
| 163 |
-
</p>
|
| 164 |
</div>
|
| 165 |
-
|
| 166 |
-
|
| 167 |
-
After making your choice, you'll proceed to the next round. 🔄
|
| 168 |
</p>
|
| 169 |
-
<
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 170 |
</p>
|
| 171 |
</div>
|
| 172 |
|
| 173 |
<div class="text-center">
|
| 174 |
-
<a href="http://71.132.14.167:6002/" target="_blank" class="btn btn-primary"><i class="fas fa-play"></i>
|
|
|
|
| 175 |
</div>
|
| 176 |
</div>
|
| 177 |
</body>
|
| 178 |
|
| 179 |
-
</html>
|
|
|
|
| 72 |
margin-right: 10px;
|
| 73 |
}
|
| 74 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 75 |
.audio-container {
|
| 76 |
text-align: center;
|
| 77 |
margin-top: 20px;
|
| 78 |
}
|
| 79 |
|
| 80 |
+
.audio-container .audio-item {
|
| 81 |
+
display: flex;
|
| 82 |
+
justify-content: center;
|
| 83 |
+
align-items: center;
|
| 84 |
+
margin-bottom: 15px;
|
| 85 |
+
}
|
| 86 |
+
|
| 87 |
+
.audio-container .audio-item span {
|
| 88 |
+
margin-right: 10px;
|
| 89 |
+
font-weight: bold;
|
| 90 |
+
}
|
| 91 |
+
|
| 92 |
+
audio {
|
| 93 |
display: inline-block;
|
| 94 |
}
|
| 95 |
</style>
|
|
|
|
| 101 |
|
| 102 |
<div id="evaluation-info" class="mb-5">
|
| 103 |
<p class="text-start">
|
| 104 |
+
<span class="section-title"><i class="fas fa-info-circle"></i>Welcome to the Speech-to-Speech (S2S)
|
| 105 |
+
Model Evaluation! 🎤</span>
|
| 106 |
In this evaluation, you will assess the performance of 4 S2S models:
|
| 107 |
<strong>ChatGPT-4o</strong>, <strong>FunAudioLLM</strong>, <strong>SpeechGPT</strong>, and
|
| 108 |
<strong>Mini-Omni</strong>.
|
| 109 |
The goal is to evaluate how well these models handle various speech tasks across different domains.
|
| 110 |
<span class="section-title"><i class="fas fa-tasks"></i>How It Works</span>
|
| 111 |
+
Once you select a specific domain and task (e.g., <em>Educational Tutoring</em> and <em>Rhythm
|
| 112 |
+
Control</em>),
|
| 113 |
you will proceed to the evaluation stage. In each round, you will be presented with an audio input. 🎵
|
| 114 |
For example:
|
| 115 |
|
| 116 |
+
<div class="audio-container">
|
| 117 |
+
<div class="audio-item">
|
| 118 |
+
<span>Audio Sample:</span>
|
| 119 |
+
<audio controls>
|
| 120 |
+
<source src="/static/audio/sample/input_audio.wav" type="audio/wav">
|
| 121 |
+
</audio>
|
| 122 |
+
</div>
|
| 123 |
+
</div>
|
| 124 |
+
The corresponding text is:
|
| 125 |
+
<em>"Say the following sentence at my speed first, then say it again very slowly:
|
| 126 |
+
'Artificial intelligence is changing the world in many ways.'" </em> 🧠
|
| 127 |
+
<small>(Note: the audio plays at 1.5x the normal speed.)</small>
|
| 128 |
|
| 129 |
+
<span class="section-title"><i class="fas fa-star"></i>Model Performance</span>
|
| 130 |
|
| 131 |
+
<div class="audio-container">
|
| 132 |
+
<div class="audio-item">
|
| 133 |
+
<span>ChatGPT-4o:</span>
|
| 134 |
<audio controls>
|
| 135 |
<source src="/static/audio/sample/4o_audio.wav" type="audio/wav">
|
| 136 |
</audio>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 137 |
</div>
|
| 138 |
+
<p style="margin: 0; text-align: left;">
|
| 139 |
+
🎙️ <strong>Speech:</strong> Partially followed the instruction on speed.
|
| 140 |
+
</p>
|
| 141 |
+
<p style="margin: 0; text-align: left;">
|
| 142 |
+
🧾 <strong>Semantics:</strong> Accurately followed the instruction, with no semantic deviation or
|
| 143 |
+
missing
|
| 144 |
+
information.
|
| 145 |
+
</p>
|
| 146 |
+
<br>
|
| 147 |
|
| 148 |
+
<div class="audio-item">
|
| 149 |
+
<span>FunAudioLLM:</span>
|
| 150 |
<audio controls>
|
| 151 |
<source src="/static/audio/sample/FunAudio_audio.wav" type="audio/wav">
|
| 152 |
</audio>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 153 |
</div>
|
| 154 |
+
<p style="margin: 0; text-align: left;">
|
| 155 |
+
🎙️ <strong>Speech:</strong> Partially followed the instruction on speed.
|
| 156 |
+
</p>
|
| 157 |
+
<p style="margin: 0; text-align: left;">
|
| 158 |
+
🧾 <strong>Semantics:</strong> Accurately followed the instruction, with no semantic deviation or
|
| 159 |
+
missing
|
| 160 |
+
information.
|
| 161 |
+
</p>
|
| 162 |
+
<br>
|
| 163 |
|
| 164 |
+
<div class="audio-item">
|
| 165 |
+
<span>SpeechGPT:</span>
|
| 166 |
<audio controls>
|
| 167 |
<source src="/static/audio/sample/SpeechGPT.wav" type="audio/wav">
|
| 168 |
</audio>
|
|
|
|
|
|
|
|
|
|
|
|
|
| 169 |
</div>
|
| 170 |
+
<p style="margin: 0; text-align: left;">
|
| 171 |
+
🎙️ <strong>Speech:</strong> Did not follow the instruction on speed.
|
| 172 |
+
</p>
|
| 173 |
+
<p style="margin: 0; text-align: left;">
|
| 174 |
+
🧾 <strong>Semantics:</strong> Partially followed the instruction, with minor semantic deviation and
|
| 175 |
+
missing information.
|
| 176 |
+
</p>
|
| 177 |
|
| 178 |
+
<br>
|
| 179 |
+
|
| 180 |
+
<div class="audio-item">
|
| 181 |
+
<span>Mini-Omni:</span>
|
| 182 |
<audio controls>
|
| 183 |
<source src="/static/audio/sample/mini-omni.wav" type="audio/wav">
|
| 184 |
</audio>
|
|
|
|
|
|
|
|
|
|
|
|
|
| 185 |
</div>
|
| 186 |
+
<p style="margin: 0; text-align: left;">
|
| 187 |
+
🎙️ <strong>Speech:</strong> Did not follow the instruction on speed.
|
|
|
|
| 188 |
</p>
|
| 189 |
+
<p style="margin: 0; text-align: left;">
|
| 190 |
+
🧾 <strong>Semantics:</strong> Did not follow the instruction, with significant semantic deviation
|
| 191 |
+
and missing information.
|
| 192 |
+
</p>
|
| 193 |
+
|
| 194 |
+
</div>
|
| 195 |
+
|
| 196 |
+
<p class="text-start">
|
| 197 |
+
After making your choice, you'll proceed to the next round. 🔄
|
| 198 |
+
</p>
|
| 199 |
+
<strong>Click the button below to start the evaluation! 🚀</strong>
|
| 200 |
</p>
|
| 201 |
</div>
|
| 202 |
|
| 203 |
<div class="text-center">
|
| 204 |
+
<a href="http://71.132.14.167:6002/" target="_blank" class="btn btn-primary"><i class="fas fa-play"></i>
|
| 205 |
+
Start Evaluation</a>
|
| 206 |
</div>
|
| 207 |
</div>
|
| 208 |
</body>
|
| 209 |
|
| 210 |
+
</html>
|