Operator ID: daft.las.functions.audio.audio_concat.AudioConcat

Description #

Audio concatenation processor that supports concatenating multiple audio files into a single audio file.

Key features #

• Supports multiple input sources: local file paths, TOS/S3 storage paths, and HTTP/HTTPS paths
• Supports output to a specified path
• Automatically handles audio files with different sample rates and channels; automatically selects the appropriate encoder based on the output format

Format support #

• WAV (.wav) - uses the pcm_s16le encoder
• MP3 (.mp3) - uses the libmp3lame encoder
• FLAC (.flac) - uses the flac encoder

Operator parameters #

Input #

Output #

An array containing the paths of the concatenated audio files. Returns the output path on success, or None on failure.

Parameters #

Examples #

The following code demonstrates how to use Daft (for distributed scenarios) to run the operator to concatenate multiple audio files.

from __future__ import annotations

import os

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

if __name__ == "__main__":
    # The converted audio will be saved to the specified TOS path. Therefore, you need to set the environment variables to ensure you have permission to write to TOS, including: ACCESS_KEY, SECRET_KEY, TOS_ENDPOINT, TOS_REGION, TOS_TEST_DIR
    TOS_TEST_DIR_URL = os.getenv("TOS_TEST_DIR_URL", "las-cn-beijing-public-online.tos-cn-beijing.volces.com")
    TOS_TEST_DIR = os.getenv("TOS_TEST_DIR", "tos_bucket")

    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",
            )
            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)

    samples = {
        "audio_paths": [
            [
                f"https://{TOS_TEST_DIR_URL}/public/archive/audio_concat/sample_a.mp3",
                f"https://{TOS_TEST_DIR_URL}/public/archive/audio_concat/sample_b.wav",
            ],
        ],
        "output_path": [f"tos://{TOS_TEST_DIR}/audio_concat/output/concatenated_audio.mp3"],
    }
    ds = daft.from_pydict(samples)

    # Using Daft to concatenate audio files
    constructor_kwargs = {
        "output_format": "mp3",
        "sample_rate": 16000,
        "extra_params": ["-b:a", "192k"],
    }

    ds = ds.with_column(
        "output_path",
        las_udf(
            AudioConcat,
            construct_args=constructor_kwargs,
            num_cpus=1,
            concurrency=1,
            batch_size=1,
        )(col("audio_paths"), col("output_path")),
    )

    ds.show()
    # ╭───────────────────┬────────────────────╮
    # │ audio_paths                    ┆ output_path                    │
    # │ ---                            ┆ ---                            │
    # │ List[String]                   ┆ String                         │
    # ╞═══════════════════╪════════════════════╡
    # │ [https://las-public-data-qa.t… ┆ tos://tos_bucket/audio_concat… │
    # ╰───────────────────┴──────────────────═─╯