Tanel Alumäe
Tanel Alumäe
No, I never tried it on Heroku.
I am afraid it's currently not possible.
Have you tried doing it yourself?
I'm planning to add English transcription system, and a language ID module so that the correct transcription path would be selected automatically for each utterance (with an option to force...
Sorry for the delay. I started thinking that probably the English adaptation that I'm planning is not going to be satisfactory for most people. I think that those who wait...
Do `make .init`
Yes, this needs to be clarified in the README. Just to let you know, it only changes the names of the speakers in the output trs files, and the recognized...
I haven't tested this particular system with Kaldi 5.2 but I'm running it in some other systems and I'm pretty sure it should work fine here too.
By far the most time-consuming part of speaker diarization is the last step -- NCLR clustering. I don't know if this algorithm is easily parallelizable or not. However, current speaker...
No, I haven't seen this. I usually use Intel's MKL, not OpenBLAS but of course it might not be possible for you. Note that you can use parallel decoding (instead...