INNER CODE UNIT · Python

pad_left

voicepaw/so-vits-svc-fork · src/so_vits_svc_fork/inference/core.py:34

        pad_left = pad_width // 2
        pad_right = pad_width - pad_left
        padded_arr = np.pad(array_, (pad_left, pad_right), "constant", constant_values=(0, 0))
        return padded_arr


@attrs.frozen(kw_only=True)
class Chunk:
    is_speech: bool
    audio: ndarray[Any, dtype[float32]]
    start: int
    end: int

    @property
    def duration(self) -> float32:
        # return self.end - self.start
        return float32(self.audio.shape[0])

View source record →