Cool_Tools/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of synced 2024-12-18 10:26:00 +01:00
Code Releases Wiki Activity

optimize real-time vc

Browse Source
This commit is contained in:
yxlllc 2023-12-26 17:05:42 +08:00
parent d7fb651f7c
commit 21775b187a
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
gui_v1.py
View File

@ -559,7 +559,7 @@ if __name__ == "__main__":
if stream_latency > 0: if stream_latency > 0:
self.delay_time += ( self.delay_time += (
1 if values["I_noise_reduce"] else -1 1 if values["I_noise_reduce"] else -1
) * values["crossfade_length"] ) * min(values["crossfade_length"], 0.04)
self.window["delay_time"].update(int(self.delay_time * 1000)) self.window["delay_time"].update(int(self.delay_time * 1000))
elif event == "O_noise_reduce": elif event == "O_noise_reduce":
self.gui_config.O_noise_reduce = values["O_noise_reduce"] self.gui_config.O_noise_reduce = values["O_noise_reduce"]
@ -774,7 +774,7 @@ if __name__ == "__main__":
# input noise reduction and resampling # input noise reduction and resampling
if self.gui_config.I_noise_reduce and self.function == "vc": if self.gui_config.I_noise_reduce and self.function == "vc":
input_wav = self.input_wav[ input_wav = self.input_wav[
-self.crossfade_frame - self.block_frame - 2 * self.zc : -self.sola_buffer_frame - self.block_frame - 2 * self.zc :
] ]
input_wav = self.tg( input_wav = self.tg(
input_wav.unsqueeze(0), self.input_wav.unsqueeze(0) input_wav.unsqueeze(0), self.input_wav.unsqueeze(0)
@ -783,7 +783,7 @@ if __name__ == "__main__":
input_wav[: self.sola_buffer_frame] += ( input_wav[: self.sola_buffer_frame] += (
self.nr_buffer * self.fade_out_window self.nr_buffer * self.fade_out_window
) )
self.nr_buffer[:] = input_wav[self.block_frame : self.block_frame + self.sola_buffer_frame] self.nr_buffer[:] = input_wav[self.block_frame :]
input_wav = torch.cat( input_wav = torch.cat(
(self.res_buffer[:], input_wav[: self.block_frame]) (self.res_buffer[:], input_wav[: self.block_frame])
) )
@ -824,7 +824,7 @@ if __name__ == "__main__":
# volume envelop mixing # volume envelop mixing
if self.gui_config.rms_mix_rate < 1 and self.function == "vc": if self.gui_config.rms_mix_rate < 1 and self.function == "vc":
rms1 = librosa.feature.rms( rms1 = librosa.feature.rms(
y=self.input_wav_res[-160 * infer_wav.shape[0] // self.zc :] y=self.input_wav_res[160 * self.skip_head : 160 * (self.skip_head + self.return_length)]
.cpu() .cpu()
.numpy(), .numpy(),
frame_length=640, frame_length=640,