microsoft
diff --git a/‎Figures/DER.jpg‎
61.2 KB b/‎Figures/DER.jpg‎
61.2 KB
diff --git a/‎Figures/cpWER.jpg‎
66.9 KB b/‎Figures/cpWER.jpg‎
66.9 KB
diff --git a/‎Figures/tcpWER.jpg‎
62.7 KB b/‎Figures/tcpWER.jpg‎
62.7 KB
diff --git a/‎README.md‎
Lines changed: 0 additions & 3 deletions b/‎README.md‎
Lines changed: 0 additions & 3 deletions
diff --git a/‎docs/vibevoice-asr.md‎
Lines changed: 7 additions & 0 deletions b/‎docs/vibevoice-asr.md‎
Lines changed: 7 additions & 0 deletions
@@ -20,9 +20,6 @@
 
 <h3>📰 News</h3>
 
-<img src="https://img.shields.io/badge/Status-New-brightgreen?style=flat" alt="New" />
-<img src="https://img.shields.io/badge/Feature-Realtime_TTS-blue?style=flat&logo=soundcharts" alt="Realtime TTS" />
-
 <strong>2026-01-21: 📣 We open-sourced <a href="docs/vibevoice-asr.md"><strong>VibeVoice-ASR</strong></a>, a unified speech-to-text model designed to handle 60-minute long-form audio in a single pass, generating structured transcriptions containing Who (Speaker), When (Timestamps), and What (Content), with support for User-Customized Context.</strong>
 
 2025-12-16: 📣 We added more experimental speakers for exploration, including multilingual voices and 11 distinct English style voices. [Try it](docs/vibevoice-realtime-0.5b.md#optional-more-experimental-voices). More speaker types will be added over time.
 
@@ -21,6 +21,13 @@ It is a unified speech-to-text model designed to handle **1-hour long-form audio
   <img src="../Figures/VibeVoice_ASR_archi.png" alt="VibeVoice ASR Architecture" width="80%">
 </p>
 
+## Evaluation
+<p align="center">
+  <img src="../Figures/DER.jpg" alt="DER" width="80%">
+  <img src="../Figures/cpWER.jpg" alt="cpWER" width="80%">
+  <img src="../Figures/tcpWER.jpg" alt="tcpWER" width="80%">
+</p>
+
 ## Installation
 We recommend to use NVIDIA Deep Learning Container to manage the CUDA environment.