Cy 'kkm' Katsnelson
Cy 'kkm' Katsnelson
@jtrmal, I just committed the new version 1.6.7. I've hit this problem couple times more, as they added more template tests for properties. I think I found a better workaround...
This is a Kaldi repository. Whet do you mean? K2 is here, btw: https://github.com/k2-fsa/k2.
My best guess is that it's not implemented. A PR is welcome. @keli78, do you have something to add?
@keli78, I'm not up to the task. There is too much work undone on Kaldi that my plate is full, and I have a dayjob (although they do intersect a...
@cding-nv?
@cding-nv, I see something not quite right here. When we compile Kaldi, we're using so called sequential threading, which means no threading at all. This is hardly efficient at our...
I think that ultimately this stems from how the numpy or other math libraries were compiled. We use sequential threading, and they usually compile multithreaded. Technically, you can compile Kaldi...
You apply CMN in nnet3/decode_semisup.sh but not in gpu_semisup.sh (variance normalization if off, mean on by default in `apply-cmvn`). Is this the root cause?
Ah, you're certainly right about the CMN with a CUDA batch decoder! /Internally, the "batch" decoder is built on top of the online decoder. Could you please run an apples-to-apples...
@dpovey, @jtrmal, I am not familiar with any encoding that treats 0xFF as the non-breaking space. In fact, it is a letter in many ISO8859 encodings (either Latin y with...