nemo_curator.models.asr.qwen_asr

Qwen3-ASR vLLM implementation of the shared ASR adapter.

This uses the same Qwen3ASRModel.LLM construction and vLLM engine settings as the nkoluguri reference. ASRStage owns mono conversion and resampling; the adapter hands one prepared batch to one transcribe call and maps results back to ASRResult positions.

Module Contents

Classes

Name	Description
`QwenASRAdapter`	Run vLLM-backed Qwen3-ASR over Curator waveform items.

Functions

Name	Description
`_qwen_asr_model_cls`	-

Data

_DEFAULT_QWEN3_ASR_MODEL

_MIN_SAMPLES

API

class nemo_curator.models.asr.qwen_asr.QwenASRAdapter(
    model_id: str = _DEFAULT_QWEN3_ASR_MODEL,
    revision: str | None = None,
    gpu_memory_utilization: float = 0.7,
    max_new_tokens: int = 4096,
    max_inference_batch_size: int = 128,
    vllm_kwargs: dict[str, typing.Any] = dict()
)

Dataclass

Run vLLM-backed Qwen3-ASR over Curator waveform items.

Every valid item in one adapter call goes to a single transcribe call, so the caller’s batch boundary is the model’s batch boundary. max_inference_batch_size is the library’s own internal cap and is passed through at construction.

revision is an adapter-owned Hugging Face option and is forwarded to both weight prefetch and the vLLM model loader.

vllm_kwargs exposes additional engine settings, following the existing Qwen-Omni adapter convention. Adapter-owned settings cannot be overridden through this mapping. Its default is empty, so normal construction exactly matches the nkoluguri reference engine arguments.

_model

Any = field(default=None, init=False, repr=False)

gpu_memory_utilization

float = 0.7

max_inference_batch_size

int = 128

max_new_tokens

int = 4096

model_id

str = _DEFAULT_QWEN3_ASR_MODEL

revision

str | None = None

vllm_kwargs

dict[str, Any] = field(default_factory=dict)

nemo_curator.models.asr.qwen_asr.QwenASRAdapter.__post_init__() -> None

nemo_curator.models.asr.qwen_asr.QwenASRAdapter._adapter_owned_model_kwargs() -> dict[str, typing.Any]

Return the qwen-asr constructor arguments owned by this adapter.

nemo_curator.models.asr.qwen_asr.QwenASRAdapter._waveform(
    item: dict[str, typing.Any]
) -> numpy.ndarray

staticmethod

nemo_curator.models.asr.qwen_asr.QwenASRAdapter.download_weights_on_node() -> None

Populate the local Hugging Face cache without allocating a GPU.

nemo_curator.models.asr.qwen_asr.QwenASRAdapter.load_model(
    num_gpus: int
) -> None

Load one worker-local Qwen3-ASR model through its vLLM backend.

nemo_curator.models.asr.qwen_asr.QwenASRAdapter.transcribe_batch(
    items: list[dict[str, typing.Any]]
) -> list[nemo_curator.models.asr.base.ASRResult]

Transcribe one adapter call while preserving input order.

nemo_curator.models.asr.qwen_asr.QwenASRAdapter.unload_model() -> None

Release the worker-local model and CUDA cache state.

nemo_curator.models.asr.qwen_asr._qwen_asr_model_cls() -> typing.Any

nemo_curator.models.asr.qwen_asr._DEFAULT_QWEN3_ASR_MODEL = 'Qwen/Qwen3-ASR-0.6B'

nemo_curator.models.asr.qwen_asr._MIN_SAMPLES = 1600