INNER CODE UNIT · Python

get_unit_f0

voicepaw/so-vits-svc-fork · src/so_vits_svc_fork/inference/core.py:131

    def get_unit_f0(
        self,
        audio: ndarray[Any, dtype[float32]],
        tran: int,
        cluster_infer_ratio: float,
        speaker: int | str,
        f0_method: Literal["crepe", "crepe-tiny", "parselmouth", "dio", "harvest"] = "dio",
    ):
        f0 = so_vits_svc_fork.f0.compute_f0(
            audio,
            sampling_rate=self.target_sample,
            hop_length=self.hop_size,
            method=f0_method,
        )
        f0, uv = so_vits_svc_fork.f0.interpolate_f0(f0)
        f0 = torch.as_tensor(f0, dtype=self.dtype, device=self.device)
        uv = torch.as_tensor(uv, dtype=self.dtype, device=self.device)
        f0 = f0 * 2 ** (tran / 12)

View source record →