1from __future__ import annotations
2
3import os
4
5import daft
6from daft import col
7
8from daft.aihc.common.udf import aihc_udf
9from daft.aihc.functions.audio.audio_size import AudioSize
10
11if __name__ == "__main__":
12    if os.getenv("DAFT_RUNNER", "native") == "ray":
13        import ray
14        ray.init(dashboard_host="0.0.0.0", ignore_reinit_error=True)
15        daft.set_runner_ray()
16    daft.set_execution_config(actor_udf_ready_timeout=6000, min_cpu_per_task=0)
17
18    # TODO: 根据实际场景准备样本数据
19    samples = {
20        "audio_paths": ["bos://bucket/test/aihc/test_data/test_audio.wav"],
21    }
22    ds = daft.from_pydict(samples)
23    ds = ds.with_column(
24        "result",
25        aihc_udf(
26            AudioSize,
27            num_cpus=1,
28            concurrency=4,
29            batch_size=8,
30        )(col("audio_paths")),
31    )
32    ds.show()