Hugging Face's logo

Spaces:
Audio-AGI
/
AudioSep
Runtime error

App Files Community
5
badayvedat commited on
Commit
5681680
•
1 Parent(s): ae29df4

Update requirements

Browse files
Files changed (2) hide show
  1. app.py +1 -1
  2. requirements.txt +3 -0
app.py CHANGED
@@ -22,7 +22,7 @@ description = """
22
  # AudioSep: Separate Anything You Describe
23
  [[Project Page]](https://audio-agi.github.io/Separate-Anything-You-Describe) [[Paper]](https://audio-agi.github.io/Separate-Anything-You-Describe/AudioSep_arXiv.pdf) [[Code]](https://github.com/Audio-AGI/AudioSep)
24
 
25
- We introduce AudioSep, a foundation model for open-domain sound separation with natural language queries.
26
  AudioSep demonstrates strong separation performance and impressivezero-shot generalization ability on
27
  numerous tasks such as audio event separation, musical instrument separation, and speech enhancement.
28
  """
 
22
  # AudioSep: Separate Anything You Describe
23
  [[Project Page]](https://audio-agi.github.io/Separate-Anything-You-Describe) [[Paper]](https://audio-agi.github.io/Separate-Anything-You-Describe/AudioSep_arXiv.pdf) [[Code]](https://github.com/Audio-AGI/AudioSep)
24
 
25
+ AudioSep is a foundation model for open-domain sound separation with natural language queries.
26
  AudioSep demonstrates strong separation performance and impressivezero-shot generalization ability on
27
  numerous tasks such as audio event separation, musical instrument separation, and speech enhancement.
28
  """
requirements.txt CHANGED
@@ -1,3 +1,6 @@
 
 
 
1
  gdown
2
  lightning==2.0.0
3
  transformers==4.28.1
 
1
+ --extra-index-url https://download.pytorch.org/whl/cu118
2
+ torch==2.0.1
3
+ torchaudio==2.0.2
4
  gdown
5
  lightning==2.0.0
6
  transformers==4.28.1