Michael Newman

You just have to set the parameters correctly in `mfcc.conf`. There are plenty of examples in the `swbd` recipe. But as you point out, there are several places in the...

I believe the two locations are in `OnlineDecoder.cc` and `RequestRawReader.h`

I think you might be seeing the same problem that I posted about in #31 If I switch in a model that I built in January, the recognition is great....

I found the problem. In order to run with the latest (batchnorm) models you need to add a line after loading ``` { bool binary; kaldi::Input ki(nnet3_rxfilename_, &binary); trans_model_->Read(ki.Stream(), binary);...

In `Nnet3LatgenFasterDecoder.cc` (in the function `Nnet3LatgenFasterDecoder::Initialize`)

See the posts above. The code needed updating to support batchnorm. After this fix everything worked fine. Note however that I haven't used this code in years so it may...

Sorry. You could try asking in the usual Kaldi help channel From: hc038 Reply-To: dialogflow/asr-server Date: Wednesday, November 11, 2020 at 6:49 AM To: dialogflow/asr-server Cc: "Mike Newman (SM)" ,...

Me too #31 What version of Kaldi are you using? Something recent? And what version did you use to build your models? It works for me if I use a...

Hi Felipe, I hit the same problem. I have absolutely the latest MagPhase from master, and all my packages appear to be up-to-date. Happy to help look into this. Let...

If I hack around this by editing `magphase.py`, it runs to completion with no obvious harm to the synthesized file ``` - f_intrp_real = interpolate.interp1d(np.arange(ncoeffs_comp), m_real_mel, kind='nearest', fill_value='extrapolate') - f_intrp_imag...