snowfall
snowfall copied to clipboard
re-run mmi_mbr_train.py
Previously, ans.phones was always the same as ans.labels after k2.compose if inner_labels=phones was requested.
https://github.com/k2-fsa/k2/pull/667 fixed this bug and we need to re-run the training script since the columns of the sparse matrix will be different.
EDITED: ans.phones will contain more zeros than ans.labels.
There are no unit tests covering inner_labels for k2.compose. That's why the bug was not found before.