athena.models.speaker_resnet

an implementation of resnet model that can be used as a sample for speaker recognition

Module Contents

Classes

SpeakerResnet

A sample implementation of resnet 34

athena.models.speaker_resnet.SUPPORTED_LOSS

class athena.models.speaker_resnet.SpeakerResnet(data_descriptions, config=None)

Bases: athena.models.base.BaseModel

A sample implementation of resnet 34 Reference to paper “Deep residual learning for image recognition” The implementation is the same as the standard resnet with 34 weighted layers, excepts using only 1/4 amount of filters to reduce computation. config:

task: “speaker_identification” or “speaker_verification”

default_config

call(self, samples, training=None)

call model

init_loss(self, loss)

initialize loss function

get_loss(self, outputs, samples, training=None)

get_eer(self, outputs, samples, training=False)

get equal error rates

make_resnet_block_layer(self, num_filter, num_blocks, stride=1)