Update app.py

app.py

@@ -76,11 +76,11 @@ se_demo = gr.Interface(
     outputs = [
         gr.Audio(label="Output Audio", type="filepath"),
     ],
-    title = "ClearVoice: Speech Enhancement",
+    title = "<a href='https://github.com/modelscope/ClearerVoice-Studio/tree/main/clearvoice' target='_blank'>ClearVoice<a/>: Speech Enhancement",
     description = ("ClearVoice is AI-powered and extracts clear speech from background noise for enhanced speech quality. It supports both 16 kHz and 48 kHz audio outputs. "
                    "To try it, simply upload your audio, or click one of the examples. "),
-    article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2206.07293' target='_blank'>FRCRN: Boosting Feature Representation Using Frequency Recurrence for Monaural Speech Enhancement</a> | <a href='https://github.com/alibabasglab/FRCRN' target='_blank'>Github Repo</a></p>"
-              "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation</a> | <a href='https://github.com/alibabasglab/MossFormer2' target='_blank'>Github Repo</a></p>"),
+    article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2206.07293' target='_blank'>FRCRN: Boosting Feature Representation Using Frequency Recurrence for Monaural Speech Enhancement</a> </p>"
+              "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation</a> </p>"),
     examples = [
         ["examples/mandarin_speech_16kHz.wav", "16000 Hz"],
         ["examples/english_speech_48kHz.wav", "48000 Hz"],
@@ -97,11 +97,11 @@ ss_demo = gr.Interface(
         gr.Audio(label="Output Audio", type="filepath"),
         gr.Audio(label="Output Audio", type="filepath"),
     ],
-    title = "ClearVoice: Speech Separation",
+    title = "<a href='https://github.com/modelscope/ClearerVoice-Studio/tree/main/clearvoice' target='_blank'>ClearVoice<a/>: Speech Separation",
     description = ("ClearVoice is powered by AI and separates individual speech from mixed audio. It supports 16 kHz and two output streams. "
                     "To try it, simply upload your audio, or click one of the examples. "),
-    article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2302.11824' target='_blank'>MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions</a> | <a href='https://github.com/alibabasglab/MossFormer' target='_blank'>Github Repo</a></p>"
-              "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation</a> | <a href='https://github.com/alibabasglab/MossFormer2' target='_blank'>Github Repo</a></p>"),
+    article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2302.11824' target='_blank'>MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions</a> </p>"
+              "<p style='text-align: center'><a href='https://arxiv.org/abs/2312.11825' target='_blank'>MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation</a> </p>"),
     examples = [
         ['examples/female_female_speech.wav'],
         ['examples/female_male_speech.wav'],
@@ -117,7 +117,7 @@ tse_demo = gr.Interface(
     outputs = [
         gr.Gallery(label="Output Video List")
     ],
-    title = "ClearVoice: Audio-Visual Speaker Extraction",
+    title = "<a href='https://github.com/modelscope/ClearerVoice-Studio/tree/main/clearvoice' target='_blank'>ClearVoice<a/>: Audio-Visual Speaker Extraction",
     description = ("ClearVoice is AI-powered and extracts each speaker's voice from a multi-speaker video using facial recognition. "
                     "To try it, simply upload your video, or click one of the examples. "),
     # article = ("<p style='text-align: center'><a href='https://arxiv.org/abs/2302.11824' target='_blank'>MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions</a> | <a href='https://github.com/alibabasglab/MossFormer' target='_blank'>Github Repo</a></p>"