🚧 This instance is under construction; expect occasional downtime. Runners available in /repos. Questions? Ask in #wikimedia-gitlab on libera.chat, or under GitLab on Phabricator.

Commit 697d094e authored by Accraze's avatar Accraze
Browse files

Add basic generation script

parent 0decbba9
from magenta.models.nsynth import utils
from magenta.models.nsynth.wavenet import fastgen
def load_encoding(fname, sample_length=None, sr=16000, ckpt='model.ckpt-200000'):
# load the audio file
audio = utils.load_audio(fname, sample_length=sample_length, sr=sr)
# encode
encoding = fastgen.encode(audio, ckpt, sample_length)
return audio, encoding
def synthesize():
fname = 'Drum_(avk).wav'
sample_length = 1000
audio, encoding = load_encoding(fname, sample_length=sample_length)
fastgen.synthesize(encoding, save_paths=['new-audio.wav'], samples_per_save=sample_length)
if __name__ == "__main__":
synthesize()
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment