Skip to content

Hotfix CPU inference #885

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
nv-kkudrynski merged 1 commit into from
Mar 24, 2021
Merged

Hotfix CPU inference #885

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

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions PyTorch/SpeechRecognition/Jasper/inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ def get_parser():
help='Eval this many steps for every worker')
parser.add_argument('--warmup_steps', default=0, type=int,
help='Burn-in period before measuring latencies')
parser.add_argument('--model_config', type=str,
parser.add_argument('--model_config', type=str, required=True,
help='Relative model config path given dataset folder')
parser.add_argument('--dataset_dir', type=str,
help='Absolute path to dataset folder')
Expand Down Expand Up @@ -324,7 +324,7 @@ def main():
if feat_proc is not None:
feats, feat_lens = feat_proc(feats, feat_lens)
else:
batch = [t.cuda(non_blocking=True) for t in batch]
batch = [t.to(device, non_blocking=True) for t in batch]
audio, audio_lens, txt, txt_lens = batch
feats, feat_lens = feat_proc(audio, audio_lens)

Expand Down