Description #

Audio duration analysis processor that accurately calculates the duration of audio content

Key features #

• Accurately calculates audio duration with precision to the second
• Supports local files, TOS storage, and binary data
• Based on librosa, a professional audio processing library

Format support #

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

Operator parameters #

Input #

Output #

Column for storing audio duration

Examples #

The following code demonstrates how to use daft to run the operator and calculate the duration of audio files.

from __future__ import annotations

import os

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

if __name__ == "__main__":
    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)

    # Use environment variables to construct the URL
    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"
        ],
    }
    df = daft.from_pydict(samples)

    # Use Daft for distributed processing
    df = df.with_column("duration_result", las_udf(AudioDuration)(col("audio_path")))

    df.show()
    # ╭────────────────────────────────┬─────────────────╮
    # │ audio_path                     ┆ duration_result │
    # │ ---                            ┆ ---             │
    # │ Utf8                           ┆ Float32         │
    # ╞════════════════════════════════╪═════════════════╡
    # │ https://las-ai-qa-online.tos-… ┆ 49.711          │
    # ╰────────────────────────────────┴─────────────────╯