python/FunASR-XL.git

			@@ -445,6 +445,12 @@
			help='Perform on "collect stats" mode',
			)
			group.add_argument(
			"--mc",
			type=bool,
			default=False,
			help="MultiChannel input",
			)
			group.add_argument(
			"--write_collected_feats",
			type=str2bool,
			default=False,
			@@ -463,6 +469,12 @@
			type=int,
			default=sys.maxsize,
			help="The maximum number update step to train",
			)
			parser.add_argument(
			"--batch_interval",
			type=int,
			default=-1,
			help="The batch interval for saving model.",
			)
			group.add_argument(
			"--patience",
			@@ -541,6 +553,12 @@
			type=int,
			default=1,
			help="The number of gradient accumulation",
			)
			group.add_argument(
			"--bias_grad_times",
			type=float,
			default=1.0,
			help="To scale the gradient of contextual related params",
			)
			group.add_argument(
			"--no_forward_run",
			@@ -629,8 +647,8 @@
			group.add_argument(
			"--init_param",
			type=str,
			action="append",
			default=[],
			nargs="*",
			help="Specify the file path used for initialization of parameters. "
			"The format is '<file_path>:<src_key>:<dst_key>:<exclude_keys>', "
			"where file_path is the model file path, "
			@@ -656,7 +674,7 @@
			"--freeze_param",
			type=str,
			default=[],
			nargs="*",
			action="append",
			help="Freeze parameters",
			)

			@@ -1147,10 +1165,10 @@
			elif args.distributed and args.simple_ddp:
			distributed_option.init_torch_distributed_pai(args)
			args.ngpu = dist.get_world_size()
			if args.dataset_type == "small":
			if args.dataset_type == "small" and args.ngpu > 0:
			if args.batch_size is not None:
			args.batch_size = args.batch_size * args.ngpu
			if args.batch_bins is not None:
			if args.batch_bins is not None and args.ngpu > 0:
			args.batch_bins = args.batch_bins * args.ngpu

			# filter samples if wav.scp and text are mismatch
			@@ -1310,6 +1328,7 @@
			data_path_and_name_and_type=args.train_data_path_and_name_and_type,
			key_file=train_key_file,
			batch_size=args.batch_size,
			mc=args.mc,
			dtype=args.train_dtype,
			num_workers=args.num_workers,
			allow_variable_data_keys=args.allow_variable_data_keys,
			@@ -1321,6 +1340,7 @@
			data_path_and_name_and_type=args.valid_data_path_and_name_and_type,
			key_file=valid_key_file,
			batch_size=args.valid_batch_size,
			mc=args.mc,
			dtype=args.train_dtype,
			num_workers=args.num_workers,
			allow_variable_data_keys=args.allow_variable_data_keys,
			@@ -1355,15 +1375,15 @@
			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,
			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,
			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":
			train_iter_factory = cls.build_iter_factory(
			@@ -1576,13 +1596,21 @@
			) -> AbsIterFactory:
			assert check_argument_types()

			if hasattr(args, "frontend_conf"):
			if args.frontend_conf is not None and "fs" in args.frontend_conf:
			dest_sample_rate = args.frontend_conf["fs"]
			else:
			dest_sample_rate = 16000
			else:
			dest_sample_rate = 16000

			dataset = ESPnetDataset(
			iter_options.data_path_and_name_and_type,
			float_dtype=args.train_dtype,
			preprocess=iter_options.preprocess_fn,
			max_cache_size=iter_options.max_cache_size,
			max_cache_fd=iter_options.max_cache_fd,
			dest_sample_rate=args.frontend_conf["fs"],
			dest_sample_rate=dest_sample_rate,
			)
			cls.check_task_requirements(
			dataset, args.allow_variable_data_keys, train=iter_options.train