Method inference

funasr/models/campplus/model.py:158–195

Run speaker embedding extraction on audio input. Args: data_in: Audio input (file path, numpy array, or list). data_lengths: Not used. key (list): Sample identifiers. tokenizer: Not used. frontend: Not used. **kwargs: M

(
        self,
        data_in,
        data_lengths=None,
        key: list = None,
        tokenizer=None,
        frontend=None,
        **kwargs,
    )

        return x

    def inference(
        self,
        data_in,
        data_lengths=None,
        key: list = None,
        tokenizer=None,
        frontend=None,
        **kwargs,
    ):
        """Run speaker embedding extraction on audio input.

        Args:
            data_in: Audio input (file path, numpy array, or list).
            data_lengths: Not used.
            key (list): Sample identifiers.
            tokenizer: Not used.
            frontend: Not used.
            **kwargs: Must include 'device' (str) and optional 'fs' (int, default 16000).

        Returns:
            tuple: (results, meta_data) where results is
                [{"spk_embedding": Tensor of shape (1, 192)}]
        """
        # extract fbank feats
        meta_data = {}
        time1 = time.perf_counter()
        audio_sample_list = load_audio_text_image_video(
            data_in, fs=16000, audio_fs=kwargs.get("fs", 16000), data_type="sound"
        )
        time2 = time.perf_counter()
        meta_data["load_data"] = f"{time2 - time1:0.3f}"
        speech, speech_lengths, speech_times = extract_feature(audio_sample_list)
        speech = speech.to(device=kwargs["device"])
        time3 = time.perf_counter()
        meta_data["extract_feat"] = f"{time3 - time2:0.3f}"
        meta_data["batch_data_time"] = np.array(speech_times).sum().item() / 16000.0
        results = [{"spk_embedding": self.forward(speech.to(torch.float32))}]
        return results, meta_data