Description #

Splits audio by duration, supporting splitting by fixed duration.

Key features #

• Splits audio into multiple segments by specified duration.
• Supports multiple input formats:
• Local file path
• TOS/S3 storage path
• Binary data stream
• Supports segment binary output or TOS storage
• Supports minimum segment duration filtering

Format support #

• MP3 (.mp3)
• WAV (.wav)
• FLAC (.flac)
• OGG (.ogg)
• AAC (.aac)
• M4A (.m4a)

Operator parameters #

Input #

Output #

An array of structs containing audio segmentation results:

• segments: List of segment paths
• binaries: List of segment binary data (optional)

Parameters #

If a parameter does not have a default value, it is required.

Examples #

The following code demonstrates how to use Daft (for distributed environments) to run the operator to split audio by duration.

from __future__ import annotations

import os

import daft
from daft import col
from daft.las.functions.audio import AudioSplitByDuration
from daft.las.functions.udf import las_udf

if __name__ == "__main__":

    # After splitting, the audio will be saved to the specified TOS path. Therefore, environment variables must be set to ensure write permissions to TOS, including: ACCESS_KEY, SECRET_KEY, TOS_ENDPOINT, TOS_REGION, TOS_TEST_DIR
    TOS_DIR = os.getenv("TOS_TEST_DIR", "tos_bucket")
    output_tos_dir = f"tos://{TOS_DIR}/audio/audio_split_by_duration"

    if os.getenv("DAFT_RUNNER", "native") == "ray":
        import logging

        import ray

        def configure_logging():
            logging.basicConfig(
                level=logging.INFO,
                format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
                datefmt="%Y-%m-%d %H:%M:%S.%s".format(),
            )
            logging.getLogger("tracing.span").setLevel(logging.WARNING)
            logging.getLogger("daft_io.stats").setLevel(logging.WARNING)
            logging.getLogger("DaftStatisticsManager").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaScheduler").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaDispatcher").setLevel(logging.WARNING)

        ray.init(dashboard_host="0.0.0.0", runtime_env={"worker_process_setup_hook": configure_logging})
        daft.set_runner_ray()
    daft.set_execution_config(actor_udf_ready_timeout=600)
    daft.set_execution_config(min_cpu_per_task=0)

    tos_dir_url = os.getenv("TOS_DIR_URL", "las-cn-beijing-public-online.tos-cn-beijing.volces.com")
    samples = {
        "audio_path": [f"https://{tos_dir_url}/public/shared_audio_dataset/sample.mp3"],
    }
    ds = daft.from_pydict(samples)

    constructor_kwargs = {
        "output_tos_dir": output_tos_dir,
        "output_segments_binary": True,
        "segment_duration": 10.0,
        "min_segment_duration": 1.0,
    }

    ds = ds.with_column(
        "split_results",
        las_udf(AudioSplitByDuration, construct_args=constructor_kwargs)(col("audio_path")),
    )

    ds.show()
    # ╭────────────────────────────────┬────────────────────────────────────────────────────────────╮
    # │ audio_path                     ┆ split_results                                             │
    # │ ---                            ┆ ---                                                       │
    # │ Utf8                           ┆ Struct[segments: List[Utf8], binaries: List[Binary]]      │
    # ╞════════════════════════════════╪════════════════════════════════════════════════════════════╡
    # │ https://las-cn-beijing-publi-… ┆ {segments: [tos://tos_bucket/audio/audio_split_by_duration… │
    # ╰────────────────────────────────┴────────────────────────────────────────────────────────────╯