Daniel Povey

oh yes sorry On Sat, Nov 14, 2020 at 1:58 PM Yiming Wang wrote: > *@freewym* commented on this pull request. > ------------------------------ > > In espresso/criterions/k2_lf_mmi_loss.py > : >...

RE the self-loops: if they were there from the start, e.g. in H, it souldn't be necessary to add any self-loops. Regarding the normalized loss: let's not bother with that...

Thanks. Would you mind getting a Python stack trace from where the bug happened, using pdb? On Mon, Nov 16, 2020 at 11:56 PM Yiming Wang wrote: > @danpovey The...

And also is it log or tropical semiring? On Tue, Nov 17, 2020 at 2:18 PM Daniel Povey wrote: > Thanks. Would you mind getting a Python stack trace from...

Sign change is expected. Please show python stack trace

Maybe try this https://blog.richard.do/2018/03/18/how-to-debug-segmentation-fault-in-python/ On Tue, Nov 17, 2020 at 4:10 PM Yiming Wang wrote: > Sign change is expected. Please show python stack trace > > I use python3...

I can't see the problem, but here's how I suggest to debug. First, please pull the latest k2 master, install locally from the bdist .whl file that you create locally...

I don't think that problem is related. We should figure out the problem there (e.g. it might be invalid input that should have been checked better) but likely not related....

mm wait, you might be right... On Tue, Nov 17, 2020 at 5:32 PM Daniel Povey wrote: > I don't think that problem is related. > We should figure out...

I think in fsa.py where we do ans = "k2.Fsa: " + _fsa_to_str(self.arcs, False, aux_labels) there should be an if statement and do something like _fsa_vec_to_str otherwise. Haowen can you...