According to our understanding, it is not intuitive to use Model Optimizer (mo_kaldi.py) to convert Kaldi Nnet3 Model input and provide it(Kaldi Nnet3 Model) to the application demo (Live Speech Recognition Demo). In addition to using iVector as a common feature input, nnet3 also uses the following Layers, but I know that support of the nnet3 format is limited.Layers (BatchNorm, Dropout, GeneralDropout, NoOp, SpecAugmentTimeMask, FixedAffine, Linear, LogSoftmax, NaturalGradientAffine, RectifiedLinear, Tdnn)
( Reference：
https://docs.openvinotoolkit.org/2021.4/openvino_docs_MO_DG_prepare_model_convert_model_kaldi_specific_Aspire_Tdnn_Model.html
https://docs.openvino.ai/2021.4/openvino_docs_MO_DG_prepare_model_Supported_Frameworks_Layers.html#doxid-openvino-docs-m-o-d-g-prepare-model-supported-frameworks-layers)
The common and latest technology of the Kaldi toolkit is developed on Nnet3 architecture, and the training of Nnet1 architecture is quite time-consuming and the training effect is not as good as the Nnet3 model. If the Kaldi Nnet3 architecture could have more comprehensive support in the future, it will be able to provide the R & D team with a more friendly development environment. Also, it will be easier to popularize and apply on the edge application because the traditional speech recognization model (Kaldi Model) is more stable than the E2E Model.
