wassname/TTS
1
0
Fork 0
mirror of https://github.com/wassname/TTS.git synced 2026-09-09 11:16:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix VITS multi-speaker voice conversion inference

Browse Source
This commit is contained in:
Edresson Casanova
2022-12-05 09:15:01 -03:00
parent 9321b22203
commit ee20e30958
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
TTS/tts/models/vits.py
+2 -2
View File
@@ -1211,8 +1211,8 @@ class Vits(BaseTTS):
assert self.num_speakers > 0, "num_speakers have to be larger than 0."
# speaker embedding
if self.args.use_speaker_embedding and not self.args.use_d_vector_file:
g_src = self.emb_g(speaker_cond_src).unsqueeze(-1)
g_tgt = self.emb_g(speaker_cond_tgt).unsqueeze(-1)
g_src = self.emb_g(torch.from_numpy((np.array(speaker_cond_src))).unsqueeze(0)).unsqueeze(-1)
g_tgt = self.emb_g(torch.from_numpy((np.array(speaker_cond_tgt))).unsqueeze(0)).unsqueeze(-1)
elif not self.args.use_speaker_embedding and self.args.use_d_vector_file:
g_src = F.normalize(speaker_cond_src).unsqueeze(-1)
g_tgt = F.normalize(speaker_cond_tgt).unsqueeze(-1)