Merge pull request #660 from alibaba-damo-academy/dev_lhn

hnluo

2023-06-21 786ed534670efa0652e0c46abd9b9d3d5bec8635

 funasr/datasets/small_datasets/dataset.py

@@ -9,8 +9,7 @@
from typing import Collection
from typing import Dict
from typing import Mapping
from typing import Tuple
from typing import Union
from typing import Union, List, Tuple

import kaldiio
import numpy as np
@@ -110,7 +109,7 @@
            float_dtype: str = "float32",
            int_dtype: str = "long",
            dest_sample_rate: int = 16000,
            speed_perturb: tuple = None,
            speed_perturb: Union[list, tuple] = None,
            mode: str = "train",
    ):
        assert check_argument_types()
@@ -144,7 +143,7 @@

    def _build_loader(
            self, path: str, loader_type: str
    ) -> Mapping[str, Union[np.ndarray, torch.Tensor, str, numbers.Number]]:
    ) -> Mapping[str, Union[np.ndarray, torch.Tensor, str, List[int], numbers.Number]]:
        """Helper function to instantiate Loader.

        Args:
@@ -174,6 +173,19 @@
                        raise RuntimeError(f"{k} is duplicated ({path}:{linenum})")
                    text_loader[k] = v
            return text_loader
        elif loader_type == "text_int":
            text_int_loader = {}
            with open(path, "r", encoding="utf-8") as f:
                for linenum, line in enumerate(f, 1):
                    sps = line.rstrip().split(maxsplit=1)
                    if len(sps) == 1:
                        k, v = sps[0], ""
                    else:
                        k, v = sps
                    if k in text_int_loader:
                        raise RuntimeError(f"{k} is duplicated ({path}:{linenum})")
                    text_int_loader[k] = [int(i) for i in v.split()]
            return text_int_loader
        else:
            raise RuntimeError(f"Not supported: loader_type={loader_type}")