From 8e78f655e6e658e267f5b164e417335c99e79f39 Mon Sep 17 00:00:00 2001
From: yxlllc <llc1995@sina.com>
Date: Wed, 6 Mar 2024 16:20:50 +0800
Subject: [PATCH] fix the receptive field of flow

---
 infer/lib/infer_pack/models.py | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/infer/lib/infer_pack/models.py b/infer/lib/infer_pack/models.py
index 47aa485..eece2f9 100644
--- a/infer/lib/infer_pack/models.py
+++ b/infer/lib/infer_pack/models.py
@@ -794,15 +794,15 @@ class SynthesizerTrnMs256NSFsid(nn.Module):
         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
+        z = self.flow(z_p, x_mask, g=g, reverse=True)
         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())
             length = int(return_length.item())
-            z_p = z_p[:, :, head : head + length]
+            z = z[:, :, 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)
+            nsff0 = nsff0[:, head : head + length]        
         o = self.dec(z * x_mask, nsff0, g=g)
         return o, x_mask, (z, z_p, m_p, logs_p)
 
@@ -956,15 +956,15 @@ class SynthesizerTrnMs768NSFsid(nn.Module):
         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
+        z = self.flow(z_p, x_mask, g=g, reverse=True)
         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())
             length = int(return_length.item())
-            z_p = z_p[:, :, head : head + length]
+            z = z[:, :, 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)
 
@@ -1107,14 +1107,14 @@ class SynthesizerTrnMs256NSFsid_nono(nn.Module):
         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
+        z = self.flow(z_p, x_mask, g=g, reverse=True)
         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())
             length = int(return_length.item())
-            z_p = z_p[:, :, head : head + length]
+            z = z[:, :, 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)
 
@@ -1257,14 +1257,14 @@ class SynthesizerTrnMs768NSFsid_nono(nn.Module):
         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
+        z = self.flow(z_p, x_mask, g=g, reverse=True)
         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())
             length = int(return_length.item())
-            z_p = z_p[:, :, head : head + length]
+            z = z[:, :, 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)