Method inference

funasr/auto/auto_model.py:496–596

Run model inference on input data (internal method). Handles batching, timing, and progress reporting. Called by generate() and inference_with_vad(). Typically not called directly by users. Args: input: Audio data, file path, or text (for punc model).

(
        self,
        input,
        input_len=None,
        model=None,
        kwargs=None,
        key=None,
        progress_callback=None,
        **cfg,
    )

            )

    def inference(
        self,
        input,
        input_len=None,
        model=None,
        kwargs=None,
        key=None,
        progress_callback=None,
        **cfg,
    ):
        """Run model inference on input data (internal method).

        Handles batching, timing, and progress reporting. Called by generate()
        and inference_with_vad(). Typically not called directly by users.

        Args:
            input: Audio data, file path, or text (for punc model).
            input_len (tensor, optional): Input lengths for batch.
            model (nn.Module, optional): Override model (used for VAD/PUNC/SPK sub-models).
            kwargs (dict, optional): Override kwargs (used for sub-model configs).
            key (list, optional): Sample identifiers.
            progress_callback (callable, optional): Progress reporting function.
            **cfg: Additional config merged into kwargs.

        Returns:
            list[dict]: Model inference results.
        """
        if kwargs is None:
            self._reset_runtime_configs()
        kwargs = self.kwargs if kwargs is None else kwargs
        if "cache" in kwargs:
            kwargs.pop("cache")
        deep_update(kwargs, cfg)
        model = self.model if model is None else model

        batch_size = kwargs.get("batch_size", 1)
        # if kwargs.get("device", "cpu") == "cpu":
        #     batch_size = 1

        key_list, data_list = prepare_data_iterator(
            input, input_len=input_len, data_type=kwargs.get("data_type", None), key=key
        )

        speed_stats = {}
        asr_result_list = []
        num_samples = len(data_list)
        disable_pbar = self.kwargs.get("disable_pbar", False)
        pbar = (
            tqdm(colour="blue", total=num_samples, dynamic_ncols=True) if not disable_pbar else None
        )
        time_speech_total = 0.0
        time_escape_total = 0.0
        for beg_idx in range(0, num_samples, batch_size):
            end_idx = min(num_samples, beg_idx + batch_size)
            data_batch = data_list[beg_idx:end_idx]
            key_batch = key_list[beg_idx:end_idx]
            batch = {"data_in": data_batch, "key": key_batch}