christian.schwarz/VibeVoice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
YaoyaoChang
2025-08-25 09:00:02 -07:00
parent 66d550b7f3
commit 562c4584e5
4 changed files with 12 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
assets/MOS-preference.png → assets/image/MOS-preference.png
View File
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 66 KiB

After

Width:  |  Height:  |  Size: 66 KiB

assets/VibeVoice.jpg → assets/image/VibeVoice.jpg
View File
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 334 KiB

After

Width:  |  Height:  |  Size: 334 KiB

assets/image/microphone.svg
+5
View File
@@ -0,0 +1,5 @@
<?xml version="1.0" standalone="no"?>
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" fill="#000000" version="1.1" id="Layer_1" width="128" height="128" viewBox="0 0 20 20" enable-background="new 0 0 20 20" xml:space="preserve">
<path d="M10,12L10,12c-2.2,0-4-1.8-4-4V4c0-2.2,1.8-4,4-4h0c2.2,0,4,1.8,4,4v4C14,10.2,12.2,12,10,12z"/>
<path d="M17.4,10.1c-0.5-0.3-1.1-0.1-1.4,0.4C14.8,12.7,12.5,14,10,14c-2.5,0-4.8-1.3-6.1-3.5C3.7,10,3,9.9,2.6,10.1 c-0.5,0.3-0.6,0.9-0.4,1.4c1.4,2.5,4,4.1,6.8,4.4V18H6c-0.6,0-1,0.4-1,1s0.4,1,1,1h8c0.6,0,1-0.4,1-1s-0.4-1-1-1h-3v-2.1 c2.8-0.3,5.4-1.9,6.8-4.4C18.1,11,17.9,10.4,17.4,10.1z"/>
</svg>
Side by Side

After

Width:  |  Height:  |  Size: 664 B

index.html
+7 -3
View File
@@ -116,7 +116,11 @@
<span class="sep">·</span>
<a href="https://github.com/microsoft/VibeVoice" target="_blank"><svg width="16" height="16" fill="currentColor" viewBox="0 0 16 16" style="vertical-align: text-bottom;"><path d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.012 8.012 0 0 0 16 8c0-4.42-3.58-8-8-8z"/></svg> Code</a>
<span class="sep">·</span>
<a href="https://huggingface.co/collections/microsoft/vibevoice-68a2ef24a875c44be47b034f" target="_blank">🤗 Checkpoints</a>
<a href="https://huggingface.co/collections/microsoft/vibevoice-68a2ef24a875c44be47b034f" target="_blank">🤗 Hugging Face</a>
<span class="sep">·</span>
<a href="https://aka.ms/VibeVoiceDemo" target="_blank">
<img src="assets/image/microphone.svg" alt="Demo" width="16" height="16" style="vertical-align:text-bottom;"> Demo
</a>
</p>
<p class="muted" style="margin:0;">
@@ -127,10 +131,10 @@ The model can synthesize speech up to 90 minutes long with up to 4 distinct spea
<div style="display:flex; justify-content:center; align-items:flex-start; gap:60px; margin:20px 0; width:100%;">
<div style="flex:1; text-align:center;">
<img src="assets/VibeVoice.jpg" alt="VibeVoice Framework" style="width:120%; height:400px; object-fit:contain;">
<img src="assets/image/VibeVoice.jpg" alt="VibeVoice Framework" style="width:120%; height:400px; object-fit:contain;">
</div>
<div style="flex:1; text-align:center;">
<img src="assets/MOS-preference.png" alt="MOS Preference Results" style="width:75%; height:400px; object-fit:contain;">
<img src="assets/image/MOS-preference.png" alt="MOS Preference Results" style="width:75%; height:400px; object-fit:contain;">
</div>
</div>
</header>