提交

kongdeqiang

2026-03-13 28ccfbfc51068a663a80764e14074df5edf2b5ba

 funasr/datasets/dataloader_entry.py

@@ -14,14 +14,14 @@
        frontend=frontend,
        tokenizer=tokenizer,
        is_training=True,
        **kwargs.get("dataset_conf")
        **kwargs.get("dataset_conf"),
    )
    dataset_val = dataset_class(
        kwargs.get("valid_data_set_list"),
        frontend=frontend,
        tokenizer=tokenizer,
        is_training=False,
        **kwargs.get("dataset_conf")
        **kwargs.get("dataset_conf"),
    )

    # dataloader
@@ -49,34 +49,37 @@
    def __init__(self, frontend=None, tokenizer=None, **kwargs):
        # dataset
        logging.info("Build dataloader")

        dataset_class = tables.dataset_classes.get(kwargs.get("dataset", "AudioDataset"))
        dataset_tr = dataset_class(
            kwargs.get("train_data_set_list"),
            frontend=frontend,
            tokenizer=tokenizer,
            is_training=True,
            **kwargs.get("dataset_conf")
        )
        dataset_tr = None
        # split dataset
        self.data_split_num = kwargs["dataset_conf"].get("data_split_num", 1)
        if self.data_split_num == 1:
            dataset_tr = dataset_class(
                kwargs.get("train_data_set_list"),
                frontend=frontend,
                tokenizer=tokenizer,
                is_training=True,
                **kwargs.get("dataset_conf"),
            )
        dataset_val = dataset_class(
            kwargs.get("valid_data_set_list"),
            frontend=frontend,
            tokenizer=tokenizer,
            is_training=False,
            **kwargs.get("dataset_conf")
            **kwargs.get("dataset_conf"),
        )

        self.dataset_tr = dataset_tr
        self.dataset_val = dataset_val
        self.kwargs = kwargs

        # split dataset
        self.data_split_num = kwargs["dataset_conf"].get("data_split_num", 1)
        self.dataset_class = dataset_class
        self.frontend = frontend
        self.tokenizer = tokenizer
        self.kwargs = kwargs

    def build_iter(self, epoch=0, data_split_i=0, **kwargs):
    def build_iter(self, epoch=0, data_split_i=0, start_step=0, **kwargs):

        # reload dataset slice
        if self.data_split_num > 1:
@@ -87,7 +90,7 @@
                tokenizer=self.tokenizer,
                is_training=True,
                **self.kwargs.get("dataset_conf"),
                data_split_i=data_split_i
                data_split_i=data_split_i,
            )

        # dataloader
@@ -95,7 +98,9 @@
        batch_sampler_val = None
        if batch_sampler is not None:
            batch_sampler_class = tables.batch_sampler_classes.get(batch_sampler)
            batch_sampler = batch_sampler_class(self.dataset_tr, **self.kwargs.get("dataset_conf"))
            batch_sampler = batch_sampler_class(
                self.dataset_tr, start_step=start_step, **self.kwargs.get("dataset_conf")
            )
            batch_sampler_val = batch_sampler_class(
                self.dataset_val, is_training=False, **self.kwargs.get("dataset_conf")
            )
@@ -121,14 +126,14 @@
        frontend=frontend,
        tokenizer=tokenizer,
        is_training=True,
        **kwargs.get("dataset_conf")
        **kwargs.get("dataset_conf"),
    )
    dataset_val = dataset_class(
        kwargs.get("valid_data_set_list"),
        frontend=frontend,
        tokenizer=tokenizer,
        is_training=False,
        **kwargs.get("dataset_conf")
        **kwargs.get("dataset_conf"),
    )

    return dataset_tr, dataset_val