ngraph.opset1.ops.ctc_greedy_decoder(data: Union[_pyngraph.Node, int, float, numpy.ndarray], sequence_mask: Union[_pyngraph.Node, int, float, numpy.ndarray], merge_repeated: bool = True, name: Optional[str] = None)_pyngraph.Node

Perform greedy decoding on the logits given in input (best path).

  • data – Logits on which greedy decoding is performed.

  • sequence_mask – The tensor with sequence masks for each sequence in the batch.

  • merge_repeated – The flag for merging repeated labels during the CTC calculation.

  • name – Optional name for output node.


The new node performing an CTCGreedyDecoder operation on input tensor.