File size: 684 Bytes
e8ad7b7
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
import torchaudio
from audiocraft.models import AudioGen
from audiocraft.data.audio import audio_write

model = AudioGen.get_pretrained('facebook/audiogen-medium')
model.set_generation_params(duration=5)  # generate 8 seconds.
wav = model.generate_unconditional(4)    # generates 4 unconditional audio samples
descriptions = ['dog barking', 'sirenes of an emergency vehicule', 'footsteps in a corridor']
wav = model.generate(descriptions)  # generates 3 samples.

for idx, one_wav in enumerate(wav):
    # Will save under {idx}.wav, with loudness normalization at -14 db LUFS.
    audio_write(f'{idx}', one_wav.cpu(), model.sample_rate, strategy="loudness", loudness_compressor=True)