Daniel Povey
Daniel Povey
We'll weight them, since they'll likely have different dynamic ranges. You can let the weight on MBR be 1.0 initially though. On Wed, Jan 27, 2021 at 12:15 PM Fangjun...
MMI part is unchanged for now, but later we can try replacing it with the larger graph. On Wed, Jan 27, 2021 at 1:00 PM Fangjun Kuang wrote: > For...
Abs is a very easy operation to implement for sparse tensors, since it just affects the individual values. It might be possible to just construct another sparse tensor from the...
IDK how hard it would be to test more recent PyTorch versions...
I don't believe we have examples of multi-GPU training yet, but AFAIK standard PyTorch mechanisms for multi-GPU training should work. If you try, let us know, and make a PR...
Fantastic!! On Wed, Jan 20, 2021 at 2:36 AM Piotr Żelasko wrote: > BTW I intend to finish that PR so that we can switch between single-GPU > and multi-GPU...
Kaldi's arpa2fst is not 100% simple, especially in cases where you are dealing with a language model that was pruned. There are cases, with pruned LMs, where all the n-grams...
In that paper the DenseFsaVec would be " Acceptor U describing the acoustic scores of an utterance" In k2, so far we are dealing only with state-level lattices, not determinized...
- For the optional silence, we'll have to see if it's helpful in any scenario. I think once we start using LF_MMI as part of the objective function it will...
In graph.py this line ` LG.labels[LG.labels >= labels_disambig_id_start] = 0` takes care of it.