update

shixian.shi

2023-06-27 b0f4910de6dc91c13828026fb5bdd4f15d8636f3

 funasr/datasets/small_datasets/dataset.py

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

import kaldiio
import numpy as np
@@ -111,7 +109,7 @@
            float_dtype: str = "float32",
            int_dtype: str = "long",
            dest_sample_rate: int = 16000,
            speed_perturb: Optional[list, tuple] = None,
            speed_perturb: Union[list, tuple] = None,
            mode: str = "train",
    ):
        assert check_argument_types()
@@ -145,7 +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:
@@ -175,6 +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}")