Closed durson closed 10 months ago
Can you also fix this issue (https://github.com/k2-fsa/fast_rnnt/pull/25#issuecomment-1641313800), thanks!
I fixed #25 (comment) However I preserved S > 0 requirement since otherwise it is not compatible with torchaudio and unittest was not passing.
Summary of the changes:
@durson I have added the github actions to this repo, could you sync the PR with the latest master, thanks!
Merged latest master to fork and tests are passing.
Thanks! merging! I would be very nice if you can also make a PR to https://github.com/k2-fsa/k2 (k2/python/k2/rnnt_loss.py).
Grad tensors can be useful for the full (ordinary and pruned) rnnt losses.