Converting a Kaldi* Model

A summary of the steps for optimizing and deploying a model that was trained with Kaldi*:

1. Configure the Model Optimizer for Kaldi*.
2. Convert a Kaldi* Model to produce an optimized Intermediate Representation (IR) of the model based on the trained network topology, weights, and biases values.
3. Test the model in the Intermediate Representation format using the Inference Engine in the target environment via provided Inference Engine validation application or sample applications.
4. Integrate the Inference Engine in your application to deploy the model in the target environment.

NOTE: The Model Optimizer supports only nnet1 and nnet2 format of Kaldi models. Note that nnet3 format is not supported.

Supported Topologies

• Convolutional Neural Networks (CNN):
  • Wall Street Journal CNN (wsj_cnn4b)
  • Resource Management CNN (rm_cnn4a_smbr)
• Long Short Term Memory (LSTM) Networks:
  • Resource Management LSTM (rm_lstm4f)
  • TED-LIUM LSTM (ted_lstm4f)
• Deep Neural Networks (DNN):
  • Wall Street Journal DNN (wsj_dnn5b_smbr);
  • TED-LIUM DNN (ted_dnn_smbr)

Command Line Parameters

To convert a Kaldi* model:

1. Go to the <INSTALL_DIR>/deployment_tools/model_optimizer directory.
2. Use the mo.py script to simply convert a model with the path to the input model .nnet file:

   python3 mo.py --input_model <INPUT_MODEL>.nnet

Two groups of parameters are available to convert your model:

• Framework-agnostic parameters: These parameters are used to convert any model trained in any supported framework.
• Kaldi-specific parameters: Parameters used to convert only Kaldi* models.

Using Kaldi*-Specific Conversion Parameters

The following list provides the Kaldi*-specific parameters.

Kaldi-specific parameters:
  --counts COUNTS       A file name with full path to the counts file
  --remove_output_softmax
                        Removes the Softmax layer that is the output layer

Examples of CLI Commands

• To launch the Model Optimizer for the wsj_dnn5b_smbr model with the specified .nnet file:

  python3 mo.py --input_model wsj_dnn5b_smbr.nnet

• To launch the Model Optimizer for the wsj_dnn5b_smbr model with existing file that contains counts for the last layer with biases:

  python3 mo.py --input_model wsj_dnn5b_smbr.nnet --counts wsj_dnn5b_smbr.counts

  • The Model Optimizer normalizes сounts in the following way:

    

    

    where - the counts array, element of the counts array, - number of elements in the counts array;
  • The normalized counts are subtracted from biases of the last or next to last layer (if last layer is SoftMax).
• If you want to remove the last SoftMax layer in the topology, launch the Model Optimizer with the --remove_output_softmax flag.

  python3 mo.py --input_model wsj_dnn5b_smbr.nnet --counts wsj_dnn5b_smbr.counts --remove_output_softmax

  The Model Optimizer finds the last layer of the topology and removes this layer only if it is a SoftMax layer.

NOTE: Model Optimizer can remove SoftMax layer only if the topology has one output.

Supported Kaldi* Layers

Refer to Supported Framework Layers for the list of supported standard layers.