update

app.py

@@ -289,7 +289,7 @@ with iface:
             <li>Custom CUDA kernel for inference: we provide a fused upsampling + activation kernel written in CUDA for accelerated inference speed. Our test shows 1.5 - 3x faster speed on a single A100 GPU.</li>
             <li>Improved discriminator and loss: BigVGAN-v2 is trained using a <a href="https://arxiv.org/abs/2311.14957" target="_blank">multi-scale sub-band CQT discriminator</a> and a <a href="https://arxiv.org/abs/2306.06546" target="_blank">multi-scale mel spectrogram loss</a>.</li>
             <li>Larger training data: BigVGAN-v2 is trained using datasets containing diverse audio types, including speech in multiple languages, environmental sounds, and instruments.</li>
-            <li>We provide <a href="https://huggingface.co/nvidia/BigVGAN" target="_blank">pretrained checkpoints</a> of BigVGAN-v2 using diverse audio configurations, supporting up to 44 kHz sampling rate and 512x upsampling ratio.</li>
+            <li>We provide pretrained checkpoints of BigVGAN-v2 using diverse audio configurations, supporting up to 44 kHz sampling rate and 512x upsampling ratio. See the table below for the link.</li>
         </ul>
         </div>
         """