Spaces:
Sleeping
Sleeping
File size: 7,918 Bytes
16de183 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 |
import os
from argparse import ArgumentParser
import librosa
import soundfile
import numpy as np
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("min_length >= min_interval >= hop_size is required")
if not max_sil_kept >= hop_size:
raise ValueError("max_sil_kept >= hop_size is required")
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):
start_idx = begin * self.hop_size
if len(waveform.shape) > 1:
end_idx = min(waveform.shape[1], end * self.hop_size)
return waveform[:, start_idx:end_idx]
else:
end_idx = min(waveform.shape[0], end * self.hop_size)
return waveform[start_idx:end_idx]
def slice(self, waveform):
samples = waveform.mean(axis=0) if len(waveform.shape) > 1 else 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, clip_start = None, 0
for i, rms in enumerate(rms_list):
if rms < self.threshold:
if silence_start is None:
silence_start = i
continue
if silence_start is None:
continue
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
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
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))
if not sil_tags:
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
def get_rms(
y,
frame_length=2048,
hop_length=512,
pad_mode="constant",
):
padding = (int(frame_length // 2), int(frame_length // 2))
y = np.pad(y, padding, mode=pad_mode)
axis = -1
out_strides = y.strides + tuple([y.strides[axis]])
x_shape_trimmed = list(y.shape)
x_shape_trimmed[axis] -= frame_length - 1
out_shape = tuple(x_shape_trimmed) + tuple([frame_length])
xw = np.lib.stride_tricks.as_strided(y, shape=out_shape, strides=out_strides)
if axis < 0:
target_axis = axis - 1
else:
target_axis = axis + 1
xw = np.moveaxis(xw, -1, target_axis)
slices = [slice(None)] * xw.ndim
slices[axis] = slice(0, None, hop_length)
x = xw[tuple(slices)]
power = np.mean(np.abs(x) ** 2, axis=-2, keepdims=True)
return np.sqrt(power)
def main():
parser = ArgumentParser()
parser.add_argument("audio", type=str, help="The audio to be sliced")
parser.add_argument(
"--out", type=str, help="Output directory of the sliced audio clips"
)
parser.add_argument(
"--db_thresh",
type=float,
default=-40,
help="The dB threshold for silence detection",
)
parser.add_argument(
"--min_length",
type=int,
default=5000,
help="The minimum milliseconds required for each sliced audio clip",
)
parser.add_argument(
"--min_interval",
type=int,
default=300,
help="The minimum milliseconds for a silence part to be sliced",
)
parser.add_argument(
"--hop_size", type=int, default=10, help="Frame length in milliseconds"
)
parser.add_argument(
"--max_sil_kept",
type=int,
default=500,
help="The maximum silence length kept around the sliced clip, presented in milliseconds",
)
args = parser.parse_args()
out = args.out or os.path.dirname(os.path.abspath(args.audio))
audio, sr = librosa.load(args.audio, sr=None, mono=False)
slicer = Slicer(
sr=sr,
threshold=args.db_thresh,
min_length=args.min_length,
min_interval=args.min_interval,
hop_size=args.hop_size,
max_sil_kept=args.max_sil_kept,
)
chunks = slicer.slice(audio)
if not os.path.exists(out):
os.makedirs(out)
for i, chunk in enumerate(chunks):
if len(chunk.shape) > 1:
chunk = chunk.T
soundfile.write(
os.path.join(
out,
f"{os.path.basename(args.audio).rsplit('.', maxsplit=1)[0]}_{i}.wav",
),
chunk,
sr,
)
if __name__ == "__main__":
main()
|