mirror of
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git
synced 2024-12-29 02:55:05 +08:00
chore(format): run black on dev (#1638)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
This commit is contained in:
github-actions[bot]
GitHub
parent
997a956f4f
commit
5449f84f06
41
gui_v1.py
41
gui_v1.py
@ -38,7 +38,11 @@ def phase_vocoder(a, b, fade_out, fade_in):
|
||||
deltaphase = deltaphase - 2 * np.pi * torch.floor(deltaphase / 2 / np.pi + 0.5)
|
||||
w = 2 * np.pi * torch.arange(n // 2 + 1).to(a) + deltaphase
|
||||
t = torch.arange(n).unsqueeze(-1).to(a) / n
|
||||
result = a * (fade_out ** 2) + b * (fade_in ** 2) + torch.sum(absab * torch.cos(w * t + phia), -1) * window / n
|
||||
result = (
|
||||
a * (fade_out**2)
|
||||
+ b * (fade_in**2)
|
||||
+ torch.sum(absab * torch.cos(w * t + phia), -1) * window / n
|
||||
)
|
||||
return result
|
||||
|
||||
|
||||
@ -633,7 +637,11 @@ if __name__ == "__main__":
|
||||
self.config,
|
||||
self.rvc if hasattr(self, "rvc") else None,
|
||||
)
|
||||
self.gui_config.samplerate = self.rvc.tgt_sr if self.gui_config.sr_type == "sr_model" else self.get_device_samplerate()
|
||||
self.gui_config.samplerate = (
|
||||
self.rvc.tgt_sr
|
||||
if self.gui_config.sr_type == "sr_model"
|
||||
else self.get_device_samplerate()
|
||||
)
|
||||
self.zc = self.gui_config.samplerate // 100
|
||||
self.block_frame = (
|
||||
int(
|
||||
@ -690,7 +698,9 @@ if __name__ == "__main__":
|
||||
2 * self.zc, device=self.config.device, dtype=torch.float32
|
||||
)
|
||||
self.skip_head = self.extra_frame // self.zc
|
||||
self.return_length = (self.block_frame + self.sola_buffer_frame + self.sola_search_frame) // self.zc
|
||||
self.return_length = (
|
||||
self.block_frame + self.sola_buffer_frame + self.sola_search_frame
|
||||
) // self.zc
|
||||
self.fade_in_window: torch.Tensor = (
|
||||
torch.sin(
|
||||
0.5
|
||||
@ -824,7 +834,11 @@ if __name__ == "__main__":
|
||||
# volume envelop mixing
|
||||
if self.gui_config.rms_mix_rate < 1 and self.function == "vc":
|
||||
rms1 = librosa.feature.rms(
|
||||
y=self.input_wav_res[160 * self.skip_head : 160 * (self.skip_head + self.return_length)]
|
||||
y=self.input_wav_res[
|
||||
160
|
||||
* self.skip_head : 160
|
||||
* (self.skip_head + self.return_length)
|
||||
]
|
||||
.cpu()
|
||||
.numpy(),
|
||||
frame_length=640,
|
||||
@ -874,18 +888,21 @@ if __name__ == "__main__":
|
||||
infer_wav = infer_wav[sola_offset:]
|
||||
if "privateuseone" in str(self.config.device) or not self.gui_config.use_pv:
|
||||
infer_wav[: self.sola_buffer_frame] *= self.fade_in_window
|
||||
infer_wav[: self.sola_buffer_frame] += self.sola_buffer * self.fade_out_window
|
||||
infer_wav[: self.sola_buffer_frame] += (
|
||||
self.sola_buffer * self.fade_out_window
|
||||
)
|
||||
else:
|
||||
infer_wav[: self.sola_buffer_frame] = phase_vocoder(
|
||||
self.sola_buffer,
|
||||
infer_wav[: self.sola_buffer_frame],
|
||||
self.fade_out_window,
|
||||
self.fade_in_window)
|
||||
self.sola_buffer[:] = infer_wav[self.block_frame : self.block_frame + self.sola_buffer_frame]
|
||||
if sys.platform == "darwin":
|
||||
outdata[:] = (
|
||||
infer_wav[: self.block_frame].cpu().numpy()[:, np.newaxis]
|
||||
self.fade_in_window,
|
||||
)
|
||||
self.sola_buffer[:] = infer_wav[
|
||||
self.block_frame : self.block_frame + self.sola_buffer_frame
|
||||
]
|
||||
if sys.platform == "darwin":
|
||||
outdata[:] = infer_wav[: self.block_frame].cpu().numpy()[:, np.newaxis]
|
||||
else:
|
||||
outdata[:] = (
|
||||
infer_wav[: self.block_frame].repeat(2, 1).t().cpu().numpy()
|
||||
@ -949,6 +966,8 @@ if __name__ == "__main__":
|
||||
printt("Output device: %s:%s", str(sd.default.device[1]), output_device)
|
||||
|
||||
def get_device_samplerate(self):
|
||||
return int(sd.query_devices(device=sd.default.device[0])['default_samplerate'])
|
||||
return int(
|
||||
sd.query_devices(device=sd.default.device[0])["default_samplerate"]
|
||||
)
|
||||
|
||||
gui = GUI()
|
||||
|
||||
@ -38,6 +38,7 @@ def spectral_de_normalize_torch(magnitudes):
|
||||
mel_basis = {}
|
||||
hann_window = {}
|
||||
|
||||
|
||||
def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False):
|
||||
"""Convert waveform into Linear-frequency Linear-amplitude spectrogram.
|
||||
|
||||
@ -87,6 +88,7 @@ def spectrogram_torch(y, n_fft, sampling_rate, hop_size, win_size, center=False)
|
||||
spec = torch.sqrt(spec.real.pow(2) + spec.imag.pow(2) + 1e-6)
|
||||
return spec
|
||||
|
||||
|
||||
def spec_to_mel_torch(spec, n_fft, num_mels, sampling_rate, fmin, fmax):
|
||||
# MelBasis - Cache if needed
|
||||
global mel_basis
|
||||
|
||||
@ -62,6 +62,7 @@ class RVC:
|
||||
"""
|
||||
try:
|
||||
if config.dml == True:
|
||||
|
||||
def forward_dml(ctx, x, scale):
|
||||
ctx.scale = scale
|
||||
res = x.clone().detach()
|
||||
@ -320,6 +321,7 @@ class RVC:
|
||||
def get_f0_fcpe(self, x, f0_up_key):
|
||||
if hasattr(self, "model_fcpe") == False:
|
||||
from torchfcpe import spawn_bundled_infer_model
|
||||
|
||||
printt("Loading fcpe model")
|
||||
if "privateuseone" in str(self.device):
|
||||
self.device_fcpe = "cpu"
|
||||
@ -329,7 +331,7 @@ class RVC:
|
||||
f0 = self.model_fcpe.infer(
|
||||
x.to(self.device_fcpe).unsqueeze(0).float(),
|
||||
sr=16000,
|
||||
decoder_mode='local_argmax',
|
||||
decoder_mode="local_argmax",
|
||||
threshold=0.006,
|
||||
)
|
||||
f0 *= pow(2, f0_up_key / 12)
|
||||
@ -384,21 +386,29 @@ class RVC:
|
||||
if self.if_f0 == 1:
|
||||
f0_extractor_frame = block_frame_16k + 800
|
||||
if f0method == "rmvpe":
|
||||
f0_extractor_frame = (
|
||||
5120 * ((f0_extractor_frame - 1) // 5120 + 1) - 160
|
||||
f0_extractor_frame = 5120 * ((f0_extractor_frame - 1) // 5120 + 1) - 160
|
||||
pitch, pitchf = self.get_f0(
|
||||
input_wav[-f0_extractor_frame:], self.f0_up_key, self.n_cpu, f0method
|
||||
)
|
||||
pitch, pitchf = self.get_f0(input_wav[-f0_extractor_frame: ], self.f0_up_key, self.n_cpu, f0method)
|
||||
start_frame = block_frame_16k // 160
|
||||
end_frame = len(self.cache_pitch) - (pitch.shape[0] - 4) + start_frame
|
||||
self.cache_pitch[:] = np.append(self.cache_pitch[start_frame: end_frame], pitch[3:-1])
|
||||
self.cache_pitch[:] = np.append(
|
||||
self.cache_pitch[start_frame:end_frame], pitch[3:-1]
|
||||
)
|
||||
self.cache_pitchf[:] = np.append(
|
||||
self.cache_pitchf[start_frame:end_frame], pitchf[3:-1]
|
||||
)
|
||||
t4 = ttime()
|
||||
p_len = input_wav.shape[0] // 160
|
||||
if self.if_f0 == 1:
|
||||
cache_pitch = torch.LongTensor(self.cache_pitch[-p_len: ]).to(self.device).unsqueeze(0)
|
||||
cache_pitchf = torch.FloatTensor(self.cache_pitchf[-p_len: ]).to(self.device).unsqueeze(0)
|
||||
cache_pitch = (
|
||||
torch.LongTensor(self.cache_pitch[-p_len:]).to(self.device).unsqueeze(0)
|
||||
)
|
||||
cache_pitchf = (
|
||||
torch.FloatTensor(self.cache_pitchf[-p_len:])
|
||||
.to(self.device)
|
||||
.unsqueeze(0)
|
||||
)
|
||||
feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1)
|
||||
feats = feats[:, :p_len, :]
|
||||
p_len = torch.LongTensor([p_len]).to(self.device)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user