Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR into ...

雾聪

2023-06-28 54931dd4e1a099d7d6f144c4e12e5453deb3aa26

 funasr/tasks/abs_task.py

@@ -266,6 +266,7 @@
    def build_model(cls, args: argparse.Namespace) -> FunASRModel:
        raise NotImplementedError


    @classmethod
    def get_parser(cls) -> config_argparse.ArgumentParser:
        assert check_argument_types()
@@ -1375,25 +1376,10 @@

            # 7. Build iterator factories
            if args.dataset_type == "large":
                from funasr.datasets.large_datasets.build_dataloader import ArkDataLoader
                train_iter_factory = ArkDataLoader(args.train_data_file, args.token_list, args.dataset_conf,
                                                   frontend_conf=args.frontend_conf if hasattr(args,
                                                                                               "frontend_conf") else None,
                                                   seg_dict_file=args.seg_dict_file if hasattr(args,
                                                                                               "seg_dict_file") else None,
                                                   punc_dict_file=args.punc_list if hasattr(args,
                                                                                            "punc_list") else None,
                                                   bpemodel_file=args.bpemodel if hasattr(args, "bpemodel") else None,
                                                   mode="train")
                valid_iter_factory = ArkDataLoader(args.valid_data_file, args.token_list, args.dataset_conf,
                                                   frontend_conf=args.frontend_conf if hasattr(args,
                                                                                               "frontend_conf") else None,
                                                   seg_dict_file=args.seg_dict_file if hasattr(args,
                                                                                               "seg_dict_file") else None,
                                                   punc_dict_file=args.punc_list if hasattr(args,
                                                                                            "punc_list") else None,
                                                   bpemodel_file=args.bpemodel if hasattr(args, "bpemodel") else None,
                                                   mode="eval")
                from funasr.datasets.large_datasets.build_dataloader import LargeDataLoader
                train_iter_factory = LargeDataLoader(args, mode="train")
                valid_iter_factory = LargeDataLoader(args, mode="eval")

            elif args.dataset_type == "small":
                train_iter_factory = cls.build_iter_factory(
                    args=args,