PublicMirrors/voice-changer
1
0
Fork 0
mirror of https://github.com/w-okada/voice-changer.git synced 2025-02-02 16:23:58 +03:00
Code Issues Actions Packages Projects Releases Wiki Activity

WIP LLVC

Browse Source
This commit is contained in:
w-okada 2023-11-20 07:42:07 +09:00
parent c2b031efa5
commit 6bda815669
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
server/voice_changer/LLVC/LLVCInferencer.py
View File

@ -52,6 +52,7 @@ class LLVCInferencer:
inputTensor = torch.cat([self.front_ctx, inputTensor])
self.front_ctx = inputTensor[-L * 2 :]
# すさまじい勢いでメモリリークしていく。。。？要調査
audio1, self.enc_buf, self.dec_buf, self.out_buf, self.convnet_pre_ctx = self.model(
inputTensor.unsqueeze(0).unsqueeze(0),
self.enc_buf,