speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

refine decoding process, merge flow and vocoder

Browse Source
This commit is contained in:
志浩 2024-07-10 16:36:01 +08:00
parent 04c2d487ed
commit 4f2ca562e9
1 changed files with 1 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
funasr/models/llm_asr/hifigan.py
View File

@ -464,10 +464,7 @@ class HifiGan(nn.Module):
""" """
recon_speech = self._decode(x.transpose(1, 2)).squeeze(1) recon_speech = self._decode(x.transpose(1, 2)).squeeze(1)
retval = dict( return recon_speech
recon_speech=recon_speech,
)
return retval
def collect_feats(self, **batch: torch.Tensor) -> Dict[str, torch.Tensor]: def collect_feats(self, **batch: torch.Tensor) -> Dict[str, torch.Tensor]:
pass pass