-
Notifications
You must be signed in to change notification settings - Fork 16
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Inference code #5
Comments
def audiowrite(destpath, audio, sample_rate):
'''Function to write audio'''
import soundfile as sf
destpath = os.path.abspath(destpath)
destdir = os.path.dirname(destpath)
if not os.path.exists(destdir):
os.makedirs(destdir)
sf.write(destpath, audio, sample_rate)
return
def predict_torchmodel(model, noisy_path, save_path):
assert os.path.exists(noisy_path), "noisy path error:" + noisy_path
noisy_wave, frq = sf.read(noisy_path)
assert frq == 16000, "sample rate must equal 16000"
with torch.no_grad():
net_inp = torch.tensor(noisy_wave)[None].to(torch.float32)
estimate = model.istft(model(net_inp)).squeeze(1).cpu().data.numpy().flatten()
audiowrite(save_path, estimate, frq) |
Thanks..I get this error. |
oh, sorry! To such: def predict_torchmodel(model, noisy_path, save_path):
assert os.path.exists(noisy_path), "noisy path error:" + noisy_path
noisy_wave, frq = sf.read(noisy_path)
assert frq == 16000, "sample rate must equal 16000"
with torch.no_grad():
net_inp = torch.tensor(noisy_wave)[None].to(torch.float32)
estimate = model(net_inp).squeeze(1).cpu().data.numpy().flatten()
audiowrite(save_path, estimate, frq) |
Thank you. That worked |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello, Thank you for sharing your code. Can you please the inference script as well.
The text was updated successfully, but these errors were encountered: