Skip to content

Open-Source Frontier Voice AI

Python

update asr eval results

YaoyaoChangf7c6d2dec90f
diff --git a/Figures/DER.jpg b/Figures/DER.jpg
new file mode 100644
index 0000000..6d87843
Binary files /dev/null and b/Figures/DER.jpg differ
diff --git a/Figures/cpWER.jpg b/Figures/cpWER.jpg
new file mode 100644
index 0000000..d5ef00b
Binary files /dev/null and b/Figures/cpWER.jpg differ
diff --git a/Figures/tcpWER.jpg b/Figures/tcpWER.jpg
new file mode 100644
index 0000000..b0dcb01
Binary files /dev/null and b/Figures/tcpWER.jpg differ
diff --git a/README.md b/README.md
index 41a98de..d01d56b 100644
--- a/README.md
+++ b/README.md
@@ -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.
diff --git a/docs/vibevoice-asr.md b/docs/vibevoice-asr.md
index e96214a..e1318f2 100644
--- a/docs/vibevoice-asr.md
+++ b/docs/vibevoice-asr.md
@@ -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.