Merge branch 'main' into dev_wjm_infer

jmwang66

2023-06-16 7375292887752a995cef6f77f3d837db67c981a4

 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}")