athena.data.datasets.language_set

audio dataset

Module Contents

Classes

LanguageDatasetBuilder

LanguageDatasetBuilder

class athena.data.datasets.language_set.LanguageDatasetBuilder(config=None)

Bases: athena.data.datasets.base.BaseDatasetBuilder

LanguageDatasetBuilder

property num_class

@property

Returns

the max_index of the vocabulary

Return type

int

property input_vocab_size

@property

Returns

the input vocab size

Return type

int

property sample_type

@property

Returns

sample_type of the dataset:

{
    "input": tf.int32,
    "input_length": tf.int32,
    "output": tf.int32,
    "output_length": tf.int32,
}

Return type

dict

property sample_shape

@property

Returns

sample_shape of the dataset:

{
    "input": tf.TensorShape([None]),
    "input_length": tf.TensorShape([]),
    "output": tf.TensorShape([None]),
    "output_length": tf.TensorShape([]),
}

Return type

dict

property sample_signature

@property

Returns

sample_signature of the dataset:

{
    "input": tf.TensorSpec(shape=(None, None), dtype=tf.int32),
    "input_length": tf.TensorSpec(shape=([None]), dtype=tf.int32),
    "output": tf.TensorSpec(shape=(None, None), dtype=tf.int32),
    "output_length": tf.TensorSpec(shape=([None]), dtype=tf.int32),
}

Return type

dict

default_config

preprocess_data(file_path)

load csv file

__getitem__(index)

get a sample

Parameters

index (int) – index of the entries

Returns

sample:

{
    "input": input_labels,
    "input_length": input_length,
    "output": output_labels,
    "output_length": output_length,
}

Return type

dict