Fetch the weights when the Space builds, not on the first request

Tidy the launch call and drop stray files

Roll pyharp and tidy the card description

Make the hardware a settings change, not a code change

Prune tags that predate the taxonomy

Copy the tag list from the running Space

Declare the model's own sample rate and channel count

Return audio at the format it was given

Name the model the way its authors write it

Describe what each control does to the sound

Remove committed bytecode and editor metadata

Credit the original authors and link the repository and paper

Record the model's tags, as reported by /controls

Fix the launch keywords and the taxonomy import

Bring the Space up to the pyharp example standard (taxonomy tags, __main__ guard, show_error, v0.4.0)

Correct the license and give the Space an apt emoji and gradient

Bring Space metadata up to HARP deployment guidelines

updated model card

no soundfile

added torchcodec

torchcodec error fix

adding remfx app

initial commit