neuralmonkey.decoders.ctc_decoder module

class neuralmonkey.decoders.ctc_decoder.CTCDecoder(name: str, encoder: neuralmonkey.model.stateful.TemporalStateful, vocabulary: neuralmonkey.vocabulary.Vocabulary, data_id: str, max_length: int = None, merge_repeated_targets: bool = False, merge_repeated_outputs: bool = True, beam_width: int = 1, save_checkpoint: str = None, load_checkpoint: str = None, initializers: List[Tuple[str, Callable]] = None) → None

Bases: neuralmonkey.model.model_part.ModelPart

Connectionist Temporal Classification.

See tf.nn.ctc_loss, tf.nn.ctc_greedy_decoder etc.

__init__(name: str, encoder: neuralmonkey.model.stateful.TemporalStateful, vocabulary: neuralmonkey.vocabulary.Vocabulary, data_id: str, max_length: int = None, merge_repeated_targets: bool = False, merge_repeated_outputs: bool = True, beam_width: int = 1, save_checkpoint: str = None, load_checkpoint: str = None, initializers: List[Tuple[str, Callable]] = None) → None

Initialize self. See help(type(self)) for accurate signature.

cost

decoded

feed_dict(dataset: neuralmonkey.dataset.dataset.Dataset, train: bool = False) → Dict[tensorflow.python.framework.ops.Tensor, Any]

logits

runtime_loss

train_loss