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.

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

Use torchaudio to read sph files first #1067

Open
wants to merge 20 commits into
base: master
Choose a base branch
from

Conversation

desh2608
Copy link
Collaborator

New torchaudio with ffmpeg backend can read SPH files. It doesn't seem to be any faster than sph2pipe, but at least it does not require installing new tools.

@pzelasko
Copy link
Collaborator

Did you check that it works with shorten encoded SPH? Some older LDC distributions have SPH that couldn't be opened with anything other than sph2pipe or shorten.

@desh2608
Copy link
Collaborator Author

Did you check that it works with shorten encoded SPH? Some older LDC distributions have SPH that couldn't be opened with anything other than sph2pipe or shorten.

Is it in any of the test cases? I only tried it on ICSI dataset where it works fine, but I'm not sure how those are encoded. I can add a test cases for shorten.

@pzelasko
Copy link
Collaborator

No, I don't think it's in the tests. You'd have to try something old like maybe Callhome, not sure but maybe also SWBD. I don't remember which corpora this happened with unfortunately.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants