Spaces:
No application file
No application file
File size: 3,590 Bytes
3883c60 |
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 |
import os.path
import torch
def _split(sr, audio):
import scipy.io.wavfile
import librosa
scipy.io.wavfile.write('speakeraudio.wav', sr, audio.detach().cpu().numpy())
audio, sr = librosa.load('speakeraudio.wav', sr=16000)
# Code source: Brian McFee
# License: ISC
##################
# Standard imports
import numpy as np
import matplotlib.pyplot as plt
import librosa.display
S_full, phase = librosa.magphase(librosa.stft(audio))
# We'll compare frames using cosine similarity, and aggregate similar frames
# by taking their (per-frequency) median value.
#
# To avoid being biased by local continuity, we constrain similar frames to be
# separated by at least 2 seconds.
#
# This suppresses sparse/non-repetetitive deviations from the average spectrum,
# and works well to discard vocal elements.
S_filter = librosa.decompose.nn_filter(S_full,
aggregate=np.median,
metric='cosine',
width=int(librosa.time_to_frames(2, sr=sr)))
# The output of the filter shouldn't be greater than the input
# if we assume signals are additive. Taking the pointwise minimium
# with the input spectrum forces this.
S_filter = np.minimum(S_full, S_filter)
# We can also use a margin to reduce bleed between the vocals and instrumentation masks.
# Note: the margins need not be equal for foreground and background separation
margin_i, margin_v = 2, 10
power = 2
mask_i = librosa.util.softmask(S_filter,
margin_i * (S_full - S_filter),
power=power)
mask_v = librosa.util.softmask(S_full - S_filter,
margin_v * S_filter,
power=power)
# Once we have the masks, simply multiply them with the input spectrum
# to separate the components
S_foreground = mask_v * S_full
S_background = mask_i * S_full
# S_full_audio = librosa.istft(S_full*phase)
S_foreground_audio = librosa.istft(S_foreground*phase)
S_background_audio = librosa.istft(S_background*phase)
return S_foreground_audio, S_background_audio, sr
def split(sr, audio):
import scipy.io.wavfile
scipy.io.wavfile.write('speakeraudio.wav', sr, audio.detach().cpu().numpy())
# import torchaudio
# torchaudio.save('speakeraudio.wav', audio.abs().unsqueeze(0), sr)
import demucs.separate
import shlex
# model_name = 'htdemucs'
model_name = 'htdemucs_6s'
# model_name = 'mdx_extra_q'
args = shlex.split(f'speakeraudio.wav -n {model_name} --two-stems vocals --filename {{stem}}.{{ext}} --float32')
demucs.separate.main(args)
# audio_other_files = [os.path.join('separated', model_name, f+'.wav') for f in ['bass', 'drums', 'other', 'piano', 'guitar'] if os.path.isfile(os.path.join('separated', model_name, f+'.wav'))]
# audio_other_files = [os.path.join('separated', model_name, f+'.wav') for f in ['bass', 'other', 'piano', 'guitar'] if os.path.isfile(os.path.join('separated', model_name, f+'.wav'))]
audio_vocals_file = os.path.join('separated', model_name, 'vocals.wav')
other_file = os.path.join('separated', model_name, 'no_vocals.wav')
import torchaudio
vocals, sr = torchaudio.load(audio_vocals_file)
additional, _ = torchaudio.load(other_file)
return vocals, additional, sr
# def split(sr, audio):
# return audio, audio, sr
|