Class AutoModel

funasr/auto/auto_model.py:182–1034

class AutoModel:

    def __init__(self, **kwargs):
        """Initialize AutoModel with ASR model and optional sub-models.

        Args:
            model (str): Model name (hub alias or full ID) or local path.
            device (str): Device for inference. "cuda:0", "cpu", "mps", "npu:0".
                Falls back to CPU if specified device is unavailable.
            vad_model (str, optional): VAD model for long audio segmentation.
                Enables processing of any-length audio.
            vad_kwargs (dict, optional): VAD config, e.g. {"max_single_segment_time": 60000}.
            punc_model (str, optional): Punctuation restoration model.
                Not needed for Fun-ASR-Nano/SenseVoice/Qwen3-ASR (they output punctuation natively).
            spk_model (str, optional): Speaker model for diarization ("cam++" or full model ID).
                Requires vad_model. For Qwen3-ASR, also requires forced_aligner.
            spk_mode (str, optional): Speaker diarization mode. "punc_segment" (default) or "vad_segment".
            hub (str): Model hub. "ms" (ModelScope, default) or "hf" (HuggingFace).
            ncpu (int): CPU threads (default: 4).
            disable_update (bool): Skip version check on startup.
            disable_pbar (bool): Disable tqdm progress bars.
            **kwargs: Additional model-specific parameters (passed to config.yaml overrides).

        Examples:
            >>> model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc")
            >>> model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", trust_remote_code=True,
            ...                   remote_code="./model.py", vad_model="fsmn-vad", spk_model="cam++", hub="hf")
        """
        try:
            from funasr.utils.version_checker import check_for_update

            check_for_update(disable=kwargs.get("disable_update", False))
        except:
            pass

        log_level = getattr(logging, kwargs.get("log_level", "INFO").upper())
        logging.basicConfig(level=log_level)

        model, kwargs = self.build_model(**kwargs)

        # if vad_model is not None, build vad model else None
        vad_model = kwargs.get("vad_model", None)
        vad_kwargs = {} if kwargs.get("vad_kwargs", {}) is None else kwargs.get("vad_kwargs", {})
        if vad_model is not None:
            logging.info("Building VAD model.")
            vad_kwargs["model"] = vad_model
            vad_kwargs["model_revision"] = kwargs.get("vad_model_revision", "master")
            vad_kwargs["device"] = kwargs["device"]
            vad_kwargs.setdefault("ncpu", kwargs.get("ncpu", 4))
            if "hub" in kwargs:
                vad_kwargs.setdefault("hub", kwargs["hub"])
            vad_model, vad_kwargs = self.build_model(**vad_kwargs)

        # if punc_model is not None, build punc model else None
        punc_model = kwargs.get("punc_model", None)
        punc_kwargs = {} if kwargs.get("punc_kwargs", {}) is None else kwargs.get("punc_kwargs", {})
        if punc_model is not None:
            logging.info("Building punc model.")