Add benchmark demo link alongside existing demos

README.md

@@ -22,7 +22,7 @@ tags:
 **WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning**  
 Sang-Hoon Lee and Ha-Yeong Choi · Ajou University and KT · NeurIPS 2026
 
-[Source Code](https://github.com/sh-lee-prml/WaveGen) · [Demo Page](https://wavegen26.github.io/demo) · [Spectral Forcing Demo](https://wavegen26.github.io/demo/spectral_forcing_visualization/)
+[Source Code](https://github.com/sh-lee-prml/WaveGen) · [Demo Page](https://wavegen26.github.io/demo) · [Benchmark Demo](https://sh-lee-prml.github.io/wavegen-tts-demo/) · [Spectral Forcing Demo](https://wavegen26.github.io/demo/spectral_forcing_visualization/)
 
 WaveGen generates speech directly from text and reference audio using Spectral Forcing. The models are trained on English and Mandarin Chinese speech from Emilia, using **24 kHz audio** and **50 Hz waveform patches** (480 samples per patch).