bugfix: fix the bug that no log prints while training or finetuning

志浩

2023-03-22 917162a9a74d725fc5698861b3b395e63fd051d9

 funasr/tasks/abs_task.py

@@ -1193,12 +1193,18 @@
            # logging.basicConfig() is invoked in main_worker() instead of main()
            # because it can be invoked only once in a process.
            # FIXME(kamo): Should we use logging.getLogger()?
            # BUGFIX: Remove previous handlers and reset log level
            for handler in logging.root.handlers[:]:
                logging.root.removeHandler(handler)
            logging.basicConfig(
                level=args.log_level,
                format=f"[{os.uname()[1].split('.')[0]}]"
                       f" %(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
            )
        else:
            # BUGFIX: Remove previous handlers and reset log level
            for handler in logging.root.handlers[:]:
                logging.root.removeHandler(handler)
            # Suppress logging if RANK != 0
            logging.basicConfig(
                level="ERROR",
@@ -1348,11 +1354,13 @@
            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,
                                                   mode="train")
                valid_iter_factory = ArkDataLoader(args.valid_data_file, args.token_list, args.dataset_conf,
                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,
@@ -1574,6 +1582,7 @@
            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"],
        )
        cls.check_task_requirements(
            dataset, args.allow_variable_data_keys, train=iter_options.train
@@ -1845,6 +1854,7 @@
            key_file: str = None,
            batch_size: int = 1,
            fs: dict = None,
            mc: bool = False,
            dtype: str = np.float32,
            num_workers: int = 1,
            allow_variable_data_keys: bool = False,
@@ -1863,6 +1873,7 @@
            data_path_and_name_and_type,
            float_dtype=dtype,
            fs=fs,
            mc=mc,
            preprocess=preprocess_fn,
            key_file=key_file,
        )