Skip to content

Fix mel spectrogram preprocessor allocating gigabytes of planned memory #18238

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
manuelcandales merged 2 commits into from
Mar 18, 2026
+8 −3
Merged

Fix mel spectrogram preprocessor allocating gigabytes of planned memory #18238

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
248b4c1
Fix mel spectrogram preprocessor allocating gigabytes of planned memo…
mergennachin Mar 17, 2026
a759487
Merge branch 'release/1.2' into cherry-pick-18229-by-pytorch_bot_bot_
manuelcandales Mar 18, 2026
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
11 changes: 8 additions & 3 deletions extension/audio/mel_spectrogram.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,10 +192,15 @@ def export_processor(model=None, output_file="whisper_preprocess.pte"):
if model is None:
model = WhisperAudioProcessor()

audio_tensor = torch.randn(93680)
if model.streaming:
# Streaming processes small windows per step. 2 seconds gives
# comfortable headroom while keeping the memory plan tight.
max_samples = 2 * model.sampling_rate
else:
max_samples = model.max_audio_len * model.sampling_rate
audio_tensor = torch.randn(min(93680, max_samples))
shapes_collection = torch.export.ShapesCollection()
max_n_chunks = int(model.max_audio_len * model.n_samples)
shapes_collection[audio_tensor] = {0: Dim.DYNAMIC(max=max_n_chunks)}
shapes_collection[audio_tensor] = {0: Dim.DYNAMIC(max=max_samples)}
with torch.no_grad(), torch.fx.experimental._config.patch(
backed_size_oblivious=True
):
Expand Down
Loading