Mirrors/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2025-12-16 11:48:08 +01:00
Code Issues Packages Projects Releases Wiki Activity

optimize real-time vc

Browse Source
This commit is contained in:
yxlllc
2023-12-26 16:26:01 +08:00
parent d62e80fb83
commit d7fb651f7c
3 changed files with 58 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
infer/lib/infer_pack/models.py
View File

@@ -785,16 +785,19 @@ class SynthesizerTrnMs256NSFsid(nn.Module):
nsff0: torch.Tensor,
sid: torch.Tensor,
skip_head: Optional[torch.Tensor] = None,
return_length: Optional[torch.Tensor] = None,
):
g = self.emb_g(sid).unsqueeze(-1)
m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
if skip_head is not None:
if skip_head is not None and return_length is not None:
assert isinstance(skip_head, torch.Tensor)
assert isinstance(return_length, torch.Tensor)
head = int(skip_head.item())
z_p = z_p[:, :, head:]
x_mask = x_mask[:, :, head:]
nsff0 = nsff0[:, head:]
length = int(return_length.item())
z_p = z_p[:, :, head: head + length]
x_mask = x_mask[:, :, head: head + length]
nsff0 = nsff0[:, head: head + length]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec(z * x_mask, nsff0, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)
@@ -944,16 +947,19 @@ class SynthesizerTrnMs768NSFsid(nn.Module):
nsff0: torch.Tensor,
sid: torch.Tensor,
skip_head: Optional[torch.Tensor] = None,
return_length: Optional[torch.Tensor] = None,
):
g = self.emb_g(sid).unsqueeze(-1)
m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
if skip_head is not None:
if skip_head is not None and return_length is not None:
assert isinstance(skip_head, torch.Tensor)
assert isinstance(return_length, torch.Tensor)
head = int(skip_head.item())
z_p = z_p[:, :, head:]
x_mask = x_mask[:, :, head:]
nsff0 = nsff0[:, head:]
length = int(return_length.item())
z_p = z_p[:, :, head: head + length]
x_mask = x_mask[:, :, head: head + length]
nsff0 = nsff0[:, head: head + length]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec(z * x_mask, nsff0, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)
@@ -1092,15 +1098,18 @@ class SynthesizerTrnMs256NSFsid_nono(nn.Module):
phone_lengths: torch.Tensor,
sid: torch.Tensor,
skip_head: Optional[torch.Tensor] = None,
return_length: Optional[torch.Tensor] = None,
):
g = self.emb_g(sid).unsqueeze(-1)
m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
if skip_head is not None:
if skip_head is not None and return_length is not None:
assert isinstance(skip_head, torch.Tensor)
assert isinstance(return_length, torch.Tensor)
head = int(skip_head.item())
z_p = z_p[:, :, head:]
x_mask = x_mask[:, :, head:]
length = int(return_length.item())
z_p = z_p[:, :, head: head + length]
x_mask = x_mask[:, :, head: head + length]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec(z * x_mask, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)
@@ -1239,15 +1248,18 @@ class SynthesizerTrnMs768NSFsid_nono(nn.Module):
phone_lengths: torch.Tensor,
sid: torch.Tensor,
skip_head: Optional[torch.Tensor] = None,
return_length: Optional[torch.Tensor] = None,
):
g = self.emb_g(sid).unsqueeze(-1)
m_p, logs_p, x_mask = self.enc_p(phone, None, phone_lengths)
z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66666) * x_mask
if skip_head is not None:
if skip_head is not None and return_length is not None:
assert isinstance(skip_head, torch.Tensor)
assert isinstance(return_length, torch.Tensor)
head = int(skip_head.item())
z_p = z_p[:, :, head:]
x_mask = x_mask[:, :, head:]
length = int(return_length.item())
z_p = z_p[:, :, head: head + length]
x_mask = x_mask[:, :, head: head + length]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec(z * x_mask, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)