update

speech_asr

2023-04-19 58fb22cb2b8144b2e29d38327be44f3510ec8bb1

 funasr/tasks/abs_task.py

@@ -1160,7 +1160,8 @@
                    args.batch_bins = args.batch_bins * args.ngpu

        # filter samples if wav.scp and text are mismatch
        if (args.train_shape_file is None and args.dataset_type == "small") or args.train_data_file is None and args.dataset_type == "large":
        if (
                args.train_shape_file is None and args.dataset_type == "small") or args.train_data_file is None and args.dataset_type == "large":
            if not args.simple_ddp or distributed_option.dist_rank == 0:
                filter_wav_text(args.data_dir, args.train_set)
                filter_wav_text(args.data_dir, args.dev_set)
@@ -1169,8 +1170,10 @@

        if args.train_shape_file is None and args.dataset_type == "small":
            if not args.simple_ddp or distributed_option.dist_rank == 0:
                calc_shape(args.data_dir, args.train_set, args.frontend_conf, args.speech_length_min, args.speech_length_max)
                calc_shape(args.data_dir, args.dev_set, args.frontend_conf, args.speech_length_min, args.speech_length_max)
                calc_shape(args.data_dir, args.train_set, args.frontend_conf, args.speech_length_min,
                           args.speech_length_max)
                calc_shape(args.data_dir, args.dev_set, args.frontend_conf, args.speech_length_min,
                           args.speech_length_max)
            if args.simple_ddp:
                dist.barrier()
            args.train_shape_file = [os.path.join(args.data_dir, args.train_set, "speech_shape")]
@@ -1360,15 +1363,21 @@
            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,
                                                   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,
                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")
            elif args.dataset_type == "small":