espnet.mt package

espnet.mt.mt_utils

espnet.mt.mt_utils.add_results_to_json(js, nbest_hyps, char_list)[source]

Function to add N-best results to json

Parameters

  • js (dict) – groundtruth utterance dict

  • nbest_hyps (list) – list of hypothesis

  • char_list (list) – list of characters

Returns

N-best results added utterance dict

espnet.mt.mt_utils.parse_hypothesis(hyp, char_list)[source]

Function to parse hypothesis

Parameters

  • hyp (list) – recognition hypothesis

  • char_list (list) – list of characters

Returns

recognition text string

Returns

recognition token string

Returns

recognition tokenid string

espnet.mt.pytorch_backend.mt

class espnet.mt.pytorch_backend.mt.CustomConverter(idim)[source]

Bases: object

Custom batch converter for Pytorch

:param int idim : index for <pad> in the source language

espnet.mt.pytorch_backend.mt.train(args)[source]

Train with the given args

Parameters

args (Namespace) – The program arguments

espnet.mt.pytorch_backend.mt.trans(args)[source]

Decode with the given args

Parameters

args (Namespace) – The program arguments