Uni-MoE commited on
Commit
c50f577
·
verified ·
1 Parent(s): 8c131c8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -4,6 +4,9 @@
4
  <strong>Uni-MoE-TTS</strong> is the audio output module of the Uni-MoE 2.0 version. It adopts a multi-layer Transformers architecture with mixture of experts(from text tokens to audio tokens) and an innovative context-aware & long-audio chunking synthesis mechanism, enabling high-quality long-audio synthesis. Currently, it supports three distinct timbres and two languages (Chinese and English), while the function of text-controlled speech style is still in the experimental stage.
5
  </p>
6
 
 
 
 
7
 
8
  ## Installation
9
  The following instructions are for Linux installation.
 
4
  <strong>Uni-MoE-TTS</strong> is the audio output module of the Uni-MoE 2.0 version. It adopts a multi-layer Transformers architecture with mixture of experts(from text tokens to audio tokens) and an innovative context-aware & long-audio chunking synthesis mechanism, enabling high-quality long-audio synthesis. Currently, it supports three distinct timbres and two languages (Chinese and English), while the function of text-controlled speech style is still in the experimental stage.
5
  </p>
6
 
7
+ <p align="center">
8
+ <img src="TTS_result.png" alt="Performance of Uni-MoE-TTS" style="max-width: 100%; width: 100%; height: auto; border-radius: 8px; box-shadow: 0 4px 12px rgba(123, 179, 255, 0.15);">
9
+ </p>
10
 
11
  ## Installation
12
  The following instructions are for Linux installation.