zerorvc/preprocess/slicer2.py

# From https://github.com/openvpi/audio-slicer
# MIT License: https://github.com/openvpi/audio-slicer/blob/main/LICENSE
from librosa.feature import rms as get_rms


class Slicer:
    def __init__(
        self,
        sr: int,
        threshold: float = -40.0,
        min_length: int = 5000,
        min_interval: int = 300,
        hop_size: int = 20,
        max_sil_kept: int = 5000,
    ):
        if not min_length >= min_interval >= hop_size:
            raise ValueError(
                "The following condition must be satisfied: min_length >= min_interval >= hop_size"
            )
        if not max_sil_kept >= hop_size:
            raise ValueError(
                "The following condition must be satisfied: max_sil_kept >= hop_size"
            )
        min_interval = sr * min_interval / 1000
        self.threshold = 10 ** (threshold / 20.0)
        self.hop_size = round(sr * hop_size / 1000)
        self.win_size = min(round(min_interval), 4 * self.hop_size)
        self.min_length = round(sr * min_length / 1000 / self.hop_size)
        self.min_interval = round(min_interval / self.hop_size)
        self.max_sil_kept = round(sr * max_sil_kept / 1000 / self.hop_size)

    def _apply_slice(self, waveform, begin, end):
        if len(waveform.shape) > 1:
            return waveform[
                :, begin * self.hop_size : min(waveform.shape[1], end * self.hop_size)
            ]
        else:
            return waveform[
                begin * self.hop_size : min(waveform.shape[0], end * self.hop_size)
            ]

    # @timeit
    def slice(self, waveform):
        if len(waveform.shape) > 1:
            samples = waveform.mean(axis=0)
        else:
            samples = waveform
        if samples.shape[0] <= self.min_length:
            return [waveform]
        rms_list = get_rms(
            y=samples, frame_length=self.win_size, hop_length=self.hop_size
        ).squeeze(0)
        sil_tags = []
        silence_start = None
        clip_start = 0
        for i, rms in enumerate(rms_list):
            # Keep looping while frame is silent.
            if rms < self.threshold:
                # Record start of silent frames.
                if silence_start is None:
                    silence_start = i
                continue
            # Keep looping while frame is not silent and silence start has not been recorded.
            if silence_start is None:
                continue
            # Clear recorded silence start if interval is not enough or clip is too short
            is_leading_silence = silence_start == 0 and i > self.max_sil_kept
            need_slice_middle = (
                i - silence_start >= self.min_interval
                and i - clip_start >= self.min_length
            )
            if not is_leading_silence and not need_slice_middle:
                silence_start = None
                continue
            # Need slicing. Record the range of silent frames to be removed.
            if i - silence_start <= self.max_sil_kept:
                pos = rms_list[silence_start : i + 1].argmin() + silence_start
                if silence_start == 0:
                    sil_tags.append((0, pos))
                else:
                    sil_tags.append((pos, pos))
                clip_start = pos
            elif i - silence_start <= self.max_sil_kept * 2:
                pos = rms_list[
                    i - self.max_sil_kept : silence_start + self.max_sil_kept + 1
                ].argmin()
                pos += i - self.max_sil_kept
                pos_l = (
                    rms_list[
                        silence_start : silence_start + self.max_sil_kept + 1
                    ].argmin()
                    + silence_start
                )
                pos_r = (
                    rms_list[i - self.max_sil_kept : i + 1].argmin()
                    + i
                    - self.max_sil_kept
                )
                if silence_start == 0:
                    sil_tags.append((0, pos_r))
                    clip_start = pos_r
                else:
                    sil_tags.append((min(pos_l, pos), max(pos_r, pos)))
                    clip_start = max(pos_r, pos)
            else:
                pos_l = (
                    rms_list[
                        silence_start : silence_start + self.max_sil_kept + 1
                    ].argmin()
                    + silence_start
                )
                pos_r = (
                    rms_list[i - self.max_sil_kept : i + 1].argmin()
                    + i
                    - self.max_sil_kept
                )
                if silence_start == 0:
                    sil_tags.append((0, pos_r))
                else:
                    sil_tags.append((pos_l, pos_r))
                clip_start = pos_r
            silence_start = None
        # Deal with trailing silence.
        total_frames = rms_list.shape[0]
        if (
            silence_start is not None
            and total_frames - silence_start >= self.min_interval
        ):
            silence_end = min(total_frames, silence_start + self.max_sil_kept)
            pos = rms_list[silence_start : silence_end + 1].argmin() + silence_start
            sil_tags.append((pos, total_frames + 1))
        # Apply and return slices.
        if len(sil_tags) == 0:
            return [waveform]
        else:
            chunks = []
            if sil_tags[0][0] > 0:
                chunks.append(self._apply_slice(waveform, 0, sil_tags[0][0]))
            for i in range(len(sil_tags) - 1):
                chunks.append(
                    self._apply_slice(waveform, sil_tags[i][1], sil_tags[i + 1][0])
                )
            if sil_tags[-1][1] < total_frames:
                chunks.append(
                    self._apply_slice(waveform, sil_tags[-1][1], total_frames)
                )
            return chunks