Skip to content

Tacotron2 --cpu-run fix #525

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.

Sign up for GitHub

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

Merged
1 commit merged into from
May 22, 2020
Merged

Tacotron2 --cpu-run fix #525

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions PyTorch/SpeechSynthesis/Tacotron2/inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,15 +148,15 @@ def pad_sequences(batch):
return text_padded, input_lengths


def prepare_input_sequence(texts):
def prepare_input_sequence(texts, cpu_run=False):

d = []
for i,text in enumerate(texts):
d.append(torch.IntTensor(
text_to_sequence(text, ['english_cleaners'])[:]))

text_padded, input_lengths = pad_sequences(d)
if torch.cuda.is_available():
if torch.cuda.is_available() and not cpu_run:
text_padded = torch.autograd.Variable(text_padded).cuda().long()
input_lengths = torch.autograd.Variable(input_lengths).cuda().long()
else:
Expand Down Expand Up @@ -236,7 +236,7 @@ def main():

measurements = {}

sequences_padded, input_lengths = prepare_input_sequence(texts)
sequences_padded, input_lengths = prepare_input_sequence(texts, args.cpu_run)

with torch.no_grad(), MeasureTime(measurements, "tacotron2_time", args.cpu_run):
mel, mel_lengths, alignments = jitted_tacotron2(sequences_padded, input_lengths)
Expand Down
2 changes: 1 addition & 1 deletion PyTorch/SpeechSynthesis/Tacotron2/test_infer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -193,7 +193,7 @@ def main():
measurements = {}

with MeasureTime(measurements, "pre_processing", args.cpu_run):
sequences_padded, input_lengths = prepare_input_sequence(texts)
sequences_padded, input_lengths = prepare_input_sequence(texts, args.cpu_run)

with torch.no_grad():
with MeasureTime(measurements, "latency", args.cpu_run):
Expand Down