Spaces:
Build error
Build error
Update app.py
Browse files
app.py
CHANGED
@@ -17,7 +17,6 @@ AudioGPT can not directly read audios, but it has a list of tools to finish diff
|
|
17 |
AudioGPT is able to use tools in a sequence, and is loyal to the tool observation outputs rather than faking the audio content and audio file name. It will remember to provide the file name from the last tool observation, if a new audio is generated.
|
18 |
Human may provide new audios to AudioGPT with a description. The description helps AudioGPT to understand this audio, but AudioGPT should use tools to finish following tasks, rather than directly imagine from the description.
|
19 |
Overall, AudioGPT is a powerful audio dialogue assistant tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics.
|
20 |
-
|
21 |
TOOLS:
|
22 |
------
|
23 |
AudioGPT has access to the following tools:"""
|
@@ -216,7 +215,9 @@ if __name__ == '__main__':
|
|
216 |
'SoundDetection': 'cpu',
|
217 |
'Binaural': 'cuda:0',
|
218 |
'SoundExtraction': 'cuda:0',
|
219 |
-
'TargetSoundDetection': 'cuda:0'
|
|
|
|
|
220 |
})
|
221 |
with gr.Blocks(css="#chatbot {overflow:auto; height:500px;}") as demo:
|
222 |
gr.Markdown(_DESCRIPTION)
|
|
|
17 |
AudioGPT is able to use tools in a sequence, and is loyal to the tool observation outputs rather than faking the audio content and audio file name. It will remember to provide the file name from the last tool observation, if a new audio is generated.
|
18 |
Human may provide new audios to AudioGPT with a description. The description helps AudioGPT to understand this audio, but AudioGPT should use tools to finish following tasks, rather than directly imagine from the description.
|
19 |
Overall, AudioGPT is a powerful audio dialogue assistant tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics.
|
|
|
20 |
TOOLS:
|
21 |
------
|
22 |
AudioGPT has access to the following tools:"""
|
|
|
215 |
'SoundDetection': 'cpu',
|
216 |
'Binaural': 'cuda:0',
|
217 |
'SoundExtraction': 'cuda:0',
|
218 |
+
'TargetSoundDetection': 'cuda:0',
|
219 |
+
'Speech_Enh_SC': 'cuda:0',
|
220 |
+
'Speech_SS': 'cuda:0'
|
221 |
})
|
222 |
with gr.Blocks(css="#chatbot {overflow:auto; height:500px;}") as demo:
|
223 |
gr.Markdown(_DESCRIPTION)
|