Skip to content
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

Jump to bottom

Fix filling of waveform_buffer with samples for streaming inference #5267

Merged
merged 2 commits into from
Jul 4, 2023
Merged

Fix filling of waveform_buffer with samples for streaming inference #5267

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
76c878f
Fix filling of waveform_buffer with samples for streaming inference
espnetUser Jun 30, 2023
3414350
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Jun 30, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
21 changes: 10 additions & 11 deletions espnet2/bin/asr_inference_streaming.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -222,19 +222,18 @@ def apply_frontend(
speech_to_process = speech
waveform_buffer = None
else:
n_frames = (
speech.size(0) - (self.win_length - self.hop_length)
) // self.hop_length
n_residual = (
speech.size(0) - (self.win_length - self.hop_length)
) % self.hop_length
speech_to_process = speech.narrow(
0, 0, (self.win_length - self.hop_length) + n_frames * self.hop_length
)
n_frames = speech.size(0) // self.hop_length
n_residual = speech.size(0) % self.hop_length
speech_to_process = speech.narrow(0, 0, n_frames * self.hop_length)
waveform_buffer = speech.narrow(
0,
speech.size(0) - (self.win_length - self.hop_length) - n_residual,
(self.win_length - self.hop_length) + n_residual,
speech.size(0)
- (math.ceil(math.ceil(self.win_length / self.hop_length) / 2) * 2 - 1)
* self.hop_length
- n_residual,
(math.ceil(math.ceil(self.win_length / self.hop_length) / 2) * 2 - 1)
* self.hop_length
+ n_residual,
).clone()

# data: (Nsamples,) -> (1, Nsamples)
Expand Down