RVC/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2026-02-19 10:50:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

optimize real-time vc

Browse Source
This commit is contained in:
yxlllc
2023-12-26 00:23:36 +08:00
parent 78f03e7dc0
commit 3dec36568c
6 changed files with 211 additions and 135 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
infer/lib/rmvpe.py
View File

@@ -593,16 +593,18 @@ class RMVPE:
def infer_from_audio(self, audio, thred=0.03):
# torch.cuda.synchronize()
t0 = ttime()
# t0 = ttime()
if not torch.is_tensor(audio):
audio = torch.from_numpy(audio)
mel = self.mel_extractor(
torch.from_numpy(audio).float().to(self.device).unsqueeze(0), center=True
audio.float().to(self.device).unsqueeze(0), center=True
)
# print(123123123,mel.device.type)
# torch.cuda.synchronize()
t1 = ttime()
# t1 = ttime()
hidden = self.mel2hidden(mel)
# torch.cuda.synchronize()
t2 = ttime()
# t2 = ttime()
# print(234234,hidden.device.type)
if "privateuseone" not in str(self.device):
hidden = hidden.squeeze(0).cpu().numpy()
@@ -613,7 +615,7 @@ class RMVPE:
f0 = self.decode(hidden, thred=thred)
# torch.cuda.synchronize()
t3 = ttime()
# t3 = ttime()
# print("hmvpe:%s\t%s\t%s\t%s"%(t1-t0,t2-t1,t3-t2,t3-t0))
return f0