Cool_Tools/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of synced 2024-11-24 07:30:16 +01:00
Code Releases Wiki Activity

Add files via upload

Browse Source
This commit is contained in:
RVC-Boss 2023-07-11 14:46:00 +08:00 committed by GitHub
parent 1279e1dcc4
commit c69cecbc41
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 26 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
lib/infer_pack/models.py
View File

@ -631,12 +631,17 @@ class SynthesizerTrnMs256NSFsid(nn.Module):
o = self.dec(z_slice, pitchf, g=g)
return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
def infer(self, phone, phone_lengths, pitch, nsff0, sid, max_len=None):
def infer(self, phone, phone_lengths, pitch, nsff0, sid, rate=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(rate):
head=int(z_p.shape[2]*rate)
z_p=z_p[:,:,-head:]
x_mask=x_mask[:,:,-head:]
nsff0=nsff0[:,-head:]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec((z * x_mask)[:, :, :max_len], nsff0, g=g)
o = self.dec(z * x_mask, nsff0, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)
@ -742,12 +747,17 @@ class SynthesizerTrnMs768NSFsid(nn.Module):
o = self.dec(z_slice, pitchf, g=g)
return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
def infer(self, phone, phone_lengths, pitch, nsff0, sid, max_len=None):
def infer(self, phone, phone_lengths, pitch, nsff0, sid, rate=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(rate):
head=int(z_p.shape[2]*rate)
z_p=z_p[:,:,-head:]
x_mask=x_mask[:,:,-head:]
nsff0=nsff0[:,-head:]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec((z * x_mask)[:, :, :max_len], nsff0, g=g)
o = self.dec(z * x_mask, nsff0, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)
@ -844,12 +854,16 @@ class SynthesizerTrnMs256NSFsid_nono(nn.Module):
o = self.dec(z_slice, g=g)
return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
def infer(self, phone, phone_lengths, sid, max_len=None):
def infer(self, phone, phone_lengths, sid, rate=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(rate):
head=int(z_p.shape[2]*rate)
z_p=z_p[:,:,-head:]
x_mask=x_mask[:,:,-head:]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec((z * x_mask)[:, :, :max_len], g=g)
o = self.dec(z * x_mask, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)
@ -946,12 +960,16 @@ class SynthesizerTrnMs768NSFsid_nono(nn.Module):
o = self.dec(z_slice, g=g)
return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
def infer(self, phone, phone_lengths, sid, max_len=None):
def infer(self, phone, phone_lengths, sid, rate=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(rate):
head=int(z_p.shape[2]*rate)
z_p=z_p[:,:,-head:]
x_mask=x_mask[:,:,-head:]
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec((z * x_mask)[:, :, :max_len], g=g)
o = self.dec(z * x_mask, g=g)
return o, x_mask, (z, z_p, m_p, logs_p)