snowfall
snowfall copied to clipboard
k2-fsa
Moved to https://github.com/k2-fsa/icefall
I just realized that there is a slight confusion in one of our naming conventions right now. In certain situations we are using sequence_idx to mean the index into the...
I'm trying to build a topology where the "blank" is phone-specific instead of shared between phones (I believe that corresponds to Kaldi's chain topology). I added a function `build_hmm_topo_2state` which...
When I run aishell ctc_decoder.py, there's an error that I can't fix: Loading L_disambig.fst.txt Loading G.fsa.txt [F] /home/wangkaisine/k2/k2/csrc/fsa_utils.cu:int32_t k2::StringToInt(const string&):43 Check failed: ok Failed to convert b'1 to an integer...
Closes #96 @danpovey Do you have any idea how to test the code? And I am not sure how the return value is used. ~I am using `mbr_lats` instead of...
I have an idea how we could organize our models to make it easier to deal with pre-training. We could divide our model into "lower" and "upper" parts. The idea...
We should try WideResnet: https://github.com/m-wiesner/nnet_pytorch/blob/master/nnet_pytorch/models/WideResnet.py
FYI I ran the transformer training with mmi + attention with different batch sampling settings to check which sampler gives better WER. The results are from the averaged model using...
Guys, I think the fact that the model output dim (87) is less than the feedforward dim (256) leads to some wastage of parameters, especially for layers close to the...
We need to debug possible memory leaks in k2, in master and also the arc_scores branch from my repo (see a PR on k2 master). (I'm pretty sure arc_scores branch...
Hi Team, Thanks for giving us the features like K2 , Lhotse. They will be a big role in coming times. I am currently running the CTC based training framework...
