Description #

Speech recognition module – Multilingual speech-to-text solution based on the Whisper model

Key features #

• Multilingual recognition: Supports major languages including Chinese and English
• Speech translation: Recognition results can be translated into English

Recommended practices #

• Audio segments within 30 seconds support batch_size > 1 to improve processing efficiency; otherwise, it is recommended to set batch_size to 1
• Highest recognition accuracy in English scenarios

Supported models #

• openai/whisper-large-v3-turbo
• openai/whisper-large-v3
• openai/whisper-medium (Average support for Chinese)
• openai/whisper-small (Chinese output is in traditional characters)

Language support #

For the complete list of supported languages, please refer to: Supported languages list

Operator parameters #

Input #

Output #

Processed structured array, each element contains the following fields:

• asr_result: Speech recognition text result;
• timestamps: List of timestamp pairs (start/end time);
• segments: List of segmented text results

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 and convert speech to text.

from __future__ import annotations

import logging
import os

import ray

import daft
from daft import col
from daft.las.functions.audio.audio_asr_whisper import AudioAsrWhisper
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 = "openai/whisper-large-v3"
    audio_src_type = "audio_url"
    dtype = "bfloat16"
    source_language = "chinese"
    translate_to_english = False
    condition_on_prev_tokens = True
    compression_ratio_threshold = 1.35
    temperature = 0.5
    logprob_threshold = -1.0
    batch_size = 1
    rank = 0

    df = daft.from_pydict(samples)
    df = df.with_column(
        "asr_result_detail",
        las_udf(
            AudioAsrWhisper,
            construct_args={
                "audio_src_type": audio_src_type,
                "model_path": model_path,
                "model_name": model_name,
                "dtype": dtype,
                "source_language": source_language,
                "translate_to_english": translate_to_english,
                "condition_on_prev_tokens": condition_on_prev_tokens,
                "compression_ratio_threshold": compression_ratio_threshold,
                "temperature": temperature,
                "logprob_threshold": logprob_threshold,
                "batch_size": batch_size,
                "rank": rank,
            },
            num_gpus=1,
            batch_size=1,
            concurrency=1,
        )(col("audio_path")),
    )
    df.show()

    # ╭────────────────────────────────┬─────────────────────────────────────────────────────────────╮
    # │ audio_path                     ┆ asr_result_detail                                           │
    # │ ---                            ┆ ---                                                         │
    # │ Utf8                           ┆ Struct[asr_result: Utf8, timestamps: List[List[Float32]],   │
    # │                                ┆ segments: List[Utf8]]                                       │
    # ╞════════════════════════════════╪═════════════════════════════════════════════════════════════╡
    # │ tos://las-cn-beijing-publi-…   ┆ {asr_result: Visit Badaoling Great Wall,                                  │
    # │                                ┆ timesta…                                                    │
    # ╰────────────────────────────────┴─────────────────────────────────────────────────────────────╯