Small model

#34
by ShReza - opened

While installing Bark, I think it took up around 5G of memory. I believe it is the large model that I am currently using. How can I switch to the small model?

To add to the abovementioned: Bark is taking around 5 G of Hard for the model and 6 G of RAM while running. It also makes up all my CPU up to 100 percent. Pycharmkeeps crashing while running.

I am using this code to use Bark:

from transformers import pipeline
import scipy

synthesiser = pipeline("text-to-speech", "suno/bark")

speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"do_sample": True})

scipy.io.wavfile.write("bark_out.wav", rate=speech["sampling_rate"], data=speech["audio"])

I think I am calling bark API with the above code. I don't have any paid plan with hugging face. Is it why I am not getting any results?

Sign up or log in to comment