Description #

AudioLidWhisper audio language recognition processor

Key features #

• Audio decoding: supports multiple audio formats → 16kHz waveform data
• Language detection: recognizes dozens of language codes based on the Whisper-large model
• Full name mapping: automatically converts language codes to full language names

Technical features #

• Loads models based on the ModelScope framework
• 16kHz sample rate audio preprocessing pipeline

Typical application scenarios #

• ✅ Speech content analysis – multilingual audio classification
• ✅ Streaming media processing – real-time language recognition
• ✅ Speech datasets – automated language annotation

Recommendation #

• To improve accuracy, first standardize upstream audio to wav format before performing language recognition.

Operator parameters #

Input #

Output #

Structured array, each element contains:

• language_code: language code
• language_code_full_name: full English language name

Parameters #

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

Examples #

The following code demonstrates how to use daft to run the operator for audio language recognition.

from __future__ import annotations

import logging
import os

import ray

import daft
from daft import col
from daft.las.functions.audio.audio_lid_whisper import AudioLidWhisper
from daft.las.functions.udf import las_udf

if __name__ == "__main__":
    if os.getenv("DAFT_RUNNER", "ray") == "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)

        import ray

        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/.wav"
        ]
    }

    model_path = os.getenv("MODEL_PATH", "/opt/las/models")
    model_name = "iic/speech_whisper-large_lid_multilingual_pytorch"
    model_version = "v2.0.4"
    num_gpus = 1
    rank = 0

    df = daft.from_pydict(samples)
    df = df.with_column(
        "lid_result",
        las_udf(
            AudioLidWhisper,
            construct_args={
                "model_path": model_path,
                "model_name": model_name,
                "model_version": model_version,
                "rank": rank,
            },
            num_gpus=1,
            batch_size=1,
            concurrency=1,
        )(col("audio_path")),
    )
    df.show()

    # ╭────────────────────────────────┬────────────────────────────────────────────────────────────╮
    # │ audio_path                     ┆ lid_result                                                 │
    # │ ---                            ┆ ---                                                        │
    # │ Utf8                           ┆ Struct[language_code: Utf8, language_code_full_name: Utf8] │
    # ╞════════════════════════════════╪════════════════════════════════════════════════════════════╡
    # │ tos://las-cn-beijing-public-o… ┆ {language_code: zh,                                        │
    # │                                ┆ language_…                                                 │
    # ╰────────────────────────────────┴────────────────────────────────────────────────────────────╯