athena.models.asr.speech_conformer_ctc

speech transformer implementation

Module Contents

Classes

SpeechConformerCTC

Standard implementation of a SpeechTransformer. Model mainly consists of three parts:

class athena.models.asr.speech_conformer_ctc.SpeechConformerCTC(data_descriptions, config=None)

Bases: athena.models.base.BaseModel

Standard implementation of a SpeechTransformer. Model mainly consists of three parts: the x_net for input preparation and the transformer itself

default_config

call(samples, training: bool = None)

call model

compute_logit_length(input_length)

used for get logit length

_forward_encoder(speech, speech_length, training=None)

_forward_encoder_log_ctc(samples, training: bool = None)

decode(samples, hparams, lm_model=None)

Initialization of the model for decoding, decoder is called here to create predictions

Parameters

• samples – the data source to be decoded

• hparams – decoding configs are included here

• lm_model – lm model

Returns:

predictions: the corresponding decoding results

argmax(samples, hparams)

argmax for the Conformer CTC model

Parameters

• samples – the data source to be decoded

• hparams – decoding configs are included here

Returns::

predictions: the corresponding decoding results

ctc_prefix_beam_search(samples, hparams, ctc_final_layer) → List[int]

freeze_ctc_prefix_beam_search(samples, ctc_final_layer, hparams=None, beam_size=1) → List[int]

merge_ctc_sequence(seqs, blank=-1)

freeze_beam_search(samples, beam_size)

beam search for freeze only support batch=1

Parameters

• samples – the data source to be decoded

• beam_size – beam size

restore_from_pretrained_model(pretrained_model, model_type='')

restore from pretrained model