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

Robust MelDataset with heterogeneous waveform file format support and on-the-fly resampling during training #8

Merged
merged 2 commits into from
Jul 30, 2024
Merged

Robust MelDataset with heterogeneous waveform file format support and on-the-fly resampling during training #8

merged 2 commits into from
Jul 30, 2024

Conversation

L0SG
Copy link
Collaborator

@L0SG L0SG commented Jul 30, 2024 •
edited
Loading

  • Switch to librosa.load to load waveform with various file formats.
  • Remove n_cache_reuse in MelDataset.
  • Use on-the-fly resampling during training. Impact on training throughput is negligible.

lars76 and others added 2 commits July 29, 2024 18:02
@L0SG L0SG changed the title Robust MelDataset with heterogenous waveform support and on-the-fly resampling during training Robust MelDataset with heterogeneous waveform file format support and on-the-fly resampling during training Jul 30, 2024
@L0SG L0SG merged commit 188ba9e into main Jul 30, 2024
@L0SG L0SG deleted the fix_finetune_and_better_load_wav branch July 30, 2024 03:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@L0SG @lars76