Method inference

funasr/models/ctc/model.py:189–298

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,
    )

    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.
            """
        if kwargs.get("batch_size", 1) > 1:
            raise NotImplementedError("batch decoding is not implemented")

        meta_data = {}
        if (
            isinstance(data_in, torch.Tensor) and kwargs.get("data_type", "sound") == "fbank"
        ):  # fbank
            speech, speech_lengths = data_in, data_lengths
            if len(speech.shape) < 3:
                speech = speech[None, :, :]
            if speech_lengths is None:
                speech_lengths = speech.shape[1]
        else:
            # extract fbank feats
            time1 = time.perf_counter()
            audio_sample_list = load_audio_text_image_video(
                data_in,
                fs=frontend.fs,
                audio_fs=kwargs.get("fs", 16000),
                data_type=kwargs.get("data_type", "sound"),
                tokenizer=tokenizer,
            )
            time2 = time.perf_counter()
            meta_data["load_data"] = f"{time2 - time1:0.3f}"
            speech, speech_lengths = extract_fbank(
                audio_sample_list, data_type=kwargs.get("data_type", "sound"), frontend=frontend
            )
            time3 = time.perf_counter()
            meta_data["extract_feat"] = f"{time3 - time2:0.3f}"
            meta_data["batch_data_time"] = (
                speech_lengths.sum().item() * frontend.frame_shift * frontend.lfr_n / 1000
            )

        speech = speech.to(device=kwargs["device"])
        speech_lengths = speech_lengths.to(device=kwargs["device"])
        # Encoder
        encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
        if isinstance(encoder_out, tuple):