alibabasglab commited on
Commit
2e5499c
·
verified ·
1 Parent(s): 43e8301

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +3 -3
app.py CHANGED
@@ -77,7 +77,7 @@ se_demo = gr.Interface(
77
  gr.Audio(label="Output Audio", type="filepath"),
78
  ],
79
  title = "<a href='https://github.com/modelscope/ClearerVoice-Studio/tree/main/clearvoice' target='_blank'>ClearVoice<a/>: Speech Enhancement",
80
- 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. "
81
  "To try it, simply upload your audio, or click one of the examples. "),
82
  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>"
83
  "<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>"),
@@ -98,7 +98,7 @@ ss_demo = gr.Interface(
98
  gr.Audio(label="Output Audio", type="filepath"),
99
  ],
100
  title = "<a href='https://github.com/modelscope/ClearerVoice-Studio/tree/main/clearvoice' target='_blank'>ClearVoice<a/>: Speech Separation",
101
- description = ("ClearVoice is powered by AI and separates individual speech from mixed audio. It supports 16 kHz and two output streams. "
102
  "To try it, simply upload your audio, or click one of the examples. "),
103
  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>"
104
  "<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>"),
@@ -118,7 +118,7 @@ tse_demo = gr.Interface(
118
  gr.Gallery(label="Output Video List")
119
  ],
120
  title = "<a href='https://github.com/modelscope/ClearerVoice-Studio/tree/main/clearvoice' target='_blank'>ClearVoice<a/>: Audio-Visual Speaker Extraction",
121
- description = ("ClearVoice is AI-powered and extracts each speaker's voice from a multi-speaker video using facial recognition. "
122
  "To try it, simply upload your video, or click one of the examples. "),
123
  # 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>"
124
  # "<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>"),
 
77
  gr.Audio(label="Output Audio", type="filepath"),
78
  ],
79
  title = "<a href='https://github.com/modelscope/ClearerVoice-Studio/tree/main/clearvoice' target='_blank'>ClearVoice<a/>: Speech Enhancement",
80
+ description = ("ClearVoice ([Github Repo](https://github.com/modelscope/ClearerVoice-Studio/tree/main/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. "
81
  "To try it, simply upload your audio, or click one of the examples. "),
82
  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>"
83
  "<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>"),
 
98
  gr.Audio(label="Output Audio", type="filepath"),
99
  ],
100
  title = "<a href='https://github.com/modelscope/ClearerVoice-Studio/tree/main/clearvoice' target='_blank'>ClearVoice<a/>: Speech Separation",
101
+ description = ("ClearVoice ([Github Repo](https://github.com/modelscope/ClearerVoice-Studio/tree/main/clearvoice)) is powered by AI and separates individual speech from mixed audio. It supports 16 kHz and two output streams. "
102
  "To try it, simply upload your audio, or click one of the examples. "),
103
  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>"
104
  "<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>"),
 
118
  gr.Gallery(label="Output Video List")
119
  ],
120
  title = "<a href='https://github.com/modelscope/ClearerVoice-Studio/tree/main/clearvoice' target='_blank'>ClearVoice<a/>: Audio-Visual Speaker Extraction",
121
+ description = ("ClearVoice ([Github Repo](https://github.com/modelscope/ClearerVoice-Studio/tree/main/clearvoice)) is AI-powered and extracts each speaker's voice from a multi-speaker video using facial recognition. "
122
  "To try it, simply upload your video, or click one of the examples. "),
123
  # 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>"
124
  # "<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>"),