RVC/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-01-20 02:51:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #2159 from tkyaji/upgrade_librosa

Browse Source 
fix: Updated librosa to version 0.10.2
This commit is contained in:
RVC-Boss
2024-07-01 10:08:22 +08:00
committed by GitHub
parent 9899757d07 330bdd9692
commit 83d6a64e67
7 changed files with 45 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
infer/lib/uvr5_pack/lib_v5/spec_utils.py
View File

@@ -43,8 +43,8 @@ def wave_to_spectrogram(
wave_left = np.asfortranarray(wave[0])
wave_right = np.asfortranarray(wave[1])
spec_left = librosa.stft(wave_left, n_fft, hop_length=hop_length)
spec_right = librosa.stft(wave_right, n_fft, hop_length=hop_length)
spec_left = librosa.stft(wave_left, n_fft=n_fft, hop_length=hop_length)
spec_right = librosa.stft(wave_right, n_fft=n_fft, hop_length=hop_length)
spec = np.asfortranarray([spec_left, spec_right])
@@ -78,7 +78,7 @@ def wave_to_spectrogram_mt(
kwargs={"y": wave_left, "n_fft": n_fft, "hop_length": hop_length},
)
thread.start()
spec_right = librosa.stft(wave_right, n_fft, hop_length=hop_length)
spec_right = librosa.stft(wave_right, n_fft=n_fft, hop_length=hop_length)
thread.join()
spec = np.asfortranarray([spec_left, spec_right])
@@ -230,26 +230,30 @@ def cache_or_load(mix_path, inst_path, mp):
if d == len(mp.param["band"]): # high-end band
X_wave[d], _ = librosa.load(
mix_path, bp["sr"], False, dtype=np.float32, res_type=bp["res_type"]
mix_path,
sr=bp["sr"],
mono=False,
dtype=np.float32,
res_type=bp["res_type"]
)
y_wave[d], _ = librosa.load(
inst_path,
bp["sr"],
False,
sr=bp["sr"],
mono=False,
dtype=np.float32,
res_type=bp["res_type"],
)
else: # lower bands
X_wave[d] = librosa.resample(
X_wave[d + 1],
mp.param["band"][d + 1]["sr"],
bp["sr"],
orig_sr=mp.param["band"][d + 1]["sr"],
target_sr=bp["sr"],
res_type=bp["res_type"],
)
y_wave[d] = librosa.resample(
y_wave[d + 1],
mp.param["band"][d + 1]["sr"],
bp["sr"],
orig_sr=mp.param["band"][d + 1]["sr"],
target_sr=bp["sr"],
res_type=bp["res_type"],
)
@@ -401,8 +405,8 @@ def cmb_spectrogram_to_wave(spec_m, mp, extra_bins_h=None, extra_bins=None):
mp.param["mid_side_b2"],
mp.param["reverse"],
),
bp["sr"],
sr,
orig_sr=bp["sr"],
target_sr=sr,
res_type="sinc_fastest",
)
else: # mid
@@ -419,7 +423,7 @@ def cmb_spectrogram_to_wave(spec_m, mp, extra_bins_h=None, extra_bins=None):
),
)
# wave = librosa.core.resample(wave2, bp['sr'], sr, res_type="sinc_fastest")
wave = librosa.core.resample(wave2, bp["sr"], sr, res_type="scipy")
wave = librosa.resample(wave2, orig_sr=bp["sr"], target_sr=sr, res_type="scipy")
return wave.T
@@ -506,8 +510,8 @@ def ensembling(a, specs):
def stft(wave, nfft, hl):
wave_left = np.asfortranarray(wave[0])
wave_right = np.asfortranarray(wave[1])
spec_left = librosa.stft(wave_left, nfft, hop_length=hl)
spec_right = librosa.stft(wave_right, nfft, hop_length=hl)
spec_left = librosa.stft(wave_left, n_fft=nfft, hop_length=hl)
spec_right = librosa.stft(wave_right, n_fft=nfft, hop_length=hl)
spec = np.asfortranarray([spec_left, spec_right])
return spec
@@ -569,8 +573,8 @@ if __name__ == "__main__":
if d == len(mp.param["band"]): # high-end band
wave[d], _ = librosa.load(
args.input[i],
bp["sr"],
False,
sr=bp["sr"],
mono=False,
dtype=np.float32,
res_type=bp["res_type"],
)
@@ -580,8 +584,8 @@ if __name__ == "__main__":
else: # lower bands
wave[d] = librosa.resample(
wave[d + 1],
mp.param["band"][d + 1]["sr"],
bp["sr"],
orig_sr=mp.param["band"][d + 1]["sr"],
target_sr=bp["sr"],
res_type=bp["res_type"],
)

24
infer/modules/uvr5/vr.py
View File

@@ -60,20 +60,20 @@ class AudioPre:
(
X_wave[d],
_,
) = librosa.core.load( # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
) = librosa.load( # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
music_file,
bp["sr"],
False,
sr=bp["sr"],
mono=False,
dtype=np.float32,
res_type=bp["res_type"],
)
if X_wave[d].ndim == 1:
X_wave[d] = np.asfortranarray([X_wave[d], X_wave[d]])
else: # lower bands
X_wave[d] = librosa.core.resample(
X_wave[d] = librosa.resample(
X_wave[d + 1],
self.mp.param["band"][d + 1]["sr"],
bp["sr"],
orig_sr=self.mp.param["band"][d + 1]["sr"],
target_sr=bp["sr"],
res_type=bp["res_type"],
)
# Stft of wave source
@@ -241,20 +241,20 @@ class AudioPreDeEcho:
(
X_wave[d],
_,
) = librosa.core.load( # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
) = librosa.load( # 理论上librosa读取可能对某些音频有bug，应该上ffmpeg读取，但是太麻烦了弃坑
music_file,
bp["sr"],
False,
sr=bp["sr"],
mono=False,
dtype=np.float32,
res_type=bp["res_type"],
)
if X_wave[d].ndim == 1:
X_wave[d] = np.asfortranarray([X_wave[d], X_wave[d]])
else: # lower bands
X_wave[d] = librosa.core.resample(
X_wave[d] = librosa.resample(
X_wave[d + 1],
self.mp.param["band"][d + 1]["sr"],
bp["sr"],
orig_sr=self.mp.param["band"][d + 1]["sr"],
target_sr=bp["sr"],
res_type=bp["res_type"],
)
# Stft of wave source