Function read_audio

python/ray/data/read_api.py:724–821

Creates a :class:`~ray.data.Dataset` from audio files. The column names default to "amplitude" and "sample_rate". Examples: >>> import ray >>> path = "s3://anonymous@air-example-data-2/6G-audio-data-LibriSpeech-train-clean-100-flac/train-clean-100/5022/29411/5022-29411-0000

(
    paths: Union[str, List[str]],
    *,
    filesystem: Optional["pyarrow.fs.FileSystem"] = None,
    arrow_open_stream_args: Optional[Dict[str, Any]] = None,
    partition_filter: Optional[PathPartitionFilter] = None,
    partitioning: Optional[Partitioning] = None,
    include_paths: bool = False,
    ignore_missing_paths: bool = False,
    file_extensions: Optional[List[str]] = AudioDatasource._FILE_EXTENSIONS,
    shuffle: Union[Literal["files"], None] = None,
    concurrency: Optional[int] = None,
    override_num_blocks: Optional[int] = None,
    num_cpus: Optional[float] = None,
    num_gpus: Optional[float] = None,
    memory: Optional[float] = None,
    ray_remote_args: Optional[Dict[str, Any]] = None,
)

@PublicAPI(stability="alpha")
def read_audio(
    paths: Union[str, List[str]],
    *,
    filesystem: Optional["pyarrow.fs.FileSystem"] = None,
    arrow_open_stream_args: Optional[Dict[str, Any]] = None,
    partition_filter: Optional[PathPartitionFilter] = None,
    partitioning: Optional[Partitioning] = None,
    include_paths: bool = False,
    ignore_missing_paths: bool = False,
    file_extensions: Optional[List[str]] = AudioDatasource._FILE_EXTENSIONS,
    shuffle: Union[Literal["files"], None] = None,
    concurrency: Optional[int] = None,
    override_num_blocks: Optional[int] = None,
    num_cpus: Optional[float] = None,
    num_gpus: Optional[float] = None,
    memory: Optional[float] = None,
    ray_remote_args: Optional[Dict[str, Any]] = None,
):
    """Creates a :class:`~ray.data.Dataset` from audio files.

    The column names default to "amplitude" and "sample_rate".

    Examples:
        >>> import ray
        >>> path = "s3://anonymous@air-example-data-2/6G-audio-data-LibriSpeech-train-clean-100-flac/train-clean-100/5022/29411/5022-29411-0000.flac"
        >>> ds = ray.data.read_audio(path)
        >>> ds.schema()
        Column       Type
        ------       ----
        amplitude    ArrowTensorTypeV2(shape=(1, 191760), dtype=float)
        sample_rate  int64

    Args:
        paths: A single file or directory, or a list of file or directory paths.
            A list of paths can contain both files and directories.
        filesystem: The pyarrow filesystem
            implementation to read from. These filesystems are specified in the
            `pyarrow docs <https://arrow.apache.org/docs/python/api/\
            filesystems.html#filesystem-implementations>`_. Specify this parameter if
            you need to provide specific configurations to the filesystem. By default,
            the filesystem is automatically selected based on the scheme of the paths.
            For example, if the path begins with ``s3://``, the `S3FileSystem` is used.
        arrow_open_stream_args: kwargs passed to
            `pyarrow.fs.FileSystem.open_input_file <https://arrow.apache.org/docs/\
                python/generated/pyarrow.fs.FileSystem.html\
                    #pyarrow.fs.FileSystem.open_input_file>`_.
            when opening input files to read.
        partition_filter:  A
            :class:`~ray.data.datasource.partitioning.PathPartitionFilter`. Use
            with a custom callback to read only selected partitions of a dataset.
        partitioning: A :class:`~ray.data.datasource.partitioning.Partitioning` object
            that describes how paths are organized. Defaults to ``None``.
        include_paths: If ``True``, include the path to each image. File paths are
            stored in the ``'path'`` column.
        ignore_missing_paths: If True, ignores any file/directory paths in ``paths``
            that are not found. Defaults to False.
        file_extensions: A list of file extensions to filter files by.
        shuffle: If ``"files"``, randomly shuffle input files order before read.