https://uberduck.ai/ logo
Join DiscordCommunities
Powered by
# machine-learning
  • https://www.youtube.com/watch?v=vIFCV2spKtg
    h

    https://www.youtube.com/watch?v=vIFCV2spKtg▾

  • eh
    h
    eh
  • ai is a very broad term
    h
    ai is a very broad term
  • machine learning is more specific and definitely doesn't include this
    h
    machine learning is more specific and definitely doesn't include this
  • there's no learning being done, it's one static algorithm with no parameters
    h
    there's no learning being done, it's one static algorithm with no parameters
  • Do you happen to know an ML version of image resizing?
    g
    Do you happen to know an ML version of image resizing?
  • haven't looked for any
    h
    haven't looked for any
  • looking it up i see this https://scribe.rip/@amulyabadal/content-aware-image-resizing-using-deep-learning-bdddd6a50aab
    h
  • which is the same thing but it uses object recognition to identify objects to preserve
    h
    which is the same thing but it uses object recognition to identify objects to preserve
  • ,,and then that's apparently used as training data for another model
    h
    ,,and then that's apparently used as training data for another model
  • and it kinda sucks
    h
    and it kinda sucks
  • there is something wrong with this vocal remover colab
    m
    there is something wrong with this vocal remover colab

    https://cdn.discordapp.com/attachments/820353681567907901/1093154953566109766/Capture.JPG▾

  • still not working
    m
    still not working
  • update torchaudio iinm
    h
    update torchaudio iinm
  • no it was librosa
    h
    no it was librosa
  • the github page should have the fix
    h
    the github page should have the fix
  • That was a question I asked
    j
    That was a question I asked
  • just downgrade librosa to 0.9.1 or 0.9.2
    j
    just downgrade librosa to 0.9.1 or 0.9.2
  • oh, yes
    m
    oh, yes
  • ```!pip install librosa==0.9.1```
    j
    Copy code
    !pip install librosa==0.9.1
  • Create a new code cell and run this ☝️
    j
    Create a new code cell and run this ☝️
  • how do i run on ?
    m
    how do i run on ?
  • If you have trouble using any notebooks, make sure you use the correct notebooks, which are linked in the **#notebooks** channel, as those notebooks are the most up-to-date ones.
    d
    If you have trouble using any notebooks, make sure you use the correct notebooks, which are linked in the #notebooks channel, as those notebooks are the most up-to-date ones.
  • https://www.youtube.com/watch?v=TGD8zKvRxc4
    t

    https://www.youtube.com/watch?v=TGD8zKvRxc4▾

  • t

    https://cdn.discordapp.com/attachments/820353681567907901/1093500449056903188/image.png▾

  • Does anybody know why I get this specific error for 001-020 every time I run the Non-English Tacotron Notebook for training, no matter the way I set up my dataset?
    t
    Does anybody know why I get this specific error for 001-020 every time I run the Non-English Tacotron Notebook for training, no matter the way I set up my dataset?
  • https://huggingface.co/spaces/damo-vilab/modelscope-text-to-video-synthesis
    t
  • Remind me which notebook or program is useful if you want to make a model sing
    t
    Remind me which notebook or program is useful if you want to make a model sing
  • I've seen those kinds of videos of people with cloned voices singing
    t
    I've seen those kinds of videos of people with cloned voices singing
  • unlike talknet it doesn't require transcripts
    h
    unlike talknet it doesn't require transcripts
1...105510561057...1068Latest