gooofy/zamia-speech

Kaldi nnet3 without ivector model

abramovi opened this issue · 1 comments

abramovi commented

Hi,
Can I use a kaldi model that trained without ivector ?

I tried to use kaldi_decode_wav.py with this model but got:

DEBUG:root:/models/ loading model... Traceback (most recent call last): File "kaldi_decode_wav.py", line 60, in <module> kaldi_model = KaldiNNet3OnlineModel (options.modeldir, acoustic_scale=1.0, beam=7.0, frame_subsampling_factor=3) File "kaldiasr/nnet3.pyx", line 134, in kaldiasr.nnet3.KaldiNNet3OnlineModel.__cinit__ RuntimeError