Method inference

funasr/models/eres2net/model.py:105–137

Run inference on input data. Args: data_in: Input data (audio samples, file paths, or text). data_lengths: Lengths of each input sample in the batch. key: Sample identifiers. tokenizer: Tokenizer instance for text e

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

        return self.model(x)

    def inference(
        self,
        data_in,
        data_lengths=None,
        key: list = None,
        tokenizer=None,
        frontend=None,
        **kwargs,
    ):
        """Run inference on input data.
        
            Args:
                data_in: Input data (audio samples, file paths, or text).
                data_lengths: Lengths of each input sample in the batch.
                key: Sample identifiers.
                tokenizer: Tokenizer instance for text encoding/decoding.
                frontend: Audio frontend for feature extraction.
                **kwargs: Additional keyword arguments.
            """
        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