Import the module "data/[dataset_name]_dataset.py". In the file, the class called DatasetNameDataset() will be instantiated. It has to be a s

Import the module "models/[model_name]_model.py". In the file, the class called DatasetNameModel() will be instantiated. It has to be a subcl

:param magnitude_spec: magnitude spectrogram of shape [time, n_freqs] obtained from spectrogram(wav_arr)['magnitude]

Load the json format cmvn stats file and calculate cmvn Args: json_cmvn_file: cmvn stats file in json format Returns: a num

Load the kaldi format cmvn stats file and calculate cmvn Args: kaldi_cmvn_file: kaldi text style global cmvn file, which is

Checks if ONNX Runtime can use the GPU by attempting to create an InferenceSession with the CUDAExecutionProvider. Returns: True

:param log_power: in db, computed by power2db(spectrogram(wav_arr)['power']) :param min_db: minimum value of log_power in db :return: log

Initialize this class Step 1: create a dataset instance given the name [dataset_mode] Step 2: create a multi-threaded data loader.

Return a batch of data

Return the total number of images in the dataset.

Return the total number of images in the dataset.

Return the number of data in the dataset

Return the total number of images in the dataset.

Return the total number of images in the dataset.

Extract acoustic fbank feature from origin waveform. Speed perturbation and wave amplitude distortion is optional. Args: batch: a l

Extract acoustic fbank feature from origin waveform. Speed perturbation and wave amplitude distortion is optional. Args: batch: a l

Create a dataset given the option. This function wraps the class CustomDatasetDataLoader. This is the main interface between this package

Create a model given the option. This function warps the class CustomDatasetDataLoader. This is the main interface between this package and '

Return the static method <modify_commandline_options> of the dataset class.

Return the static method <modify_commandline_options> of the model class.