blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2025-04-05 19:41:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: 修复prompt_cache里面没有cache住ref_audio_path，导致每次TTS推理都需要加载一遍reference_audio的bug【首次音频帧从3.2s -> 1.7s】 (#1235)

Browse Source
This commit is contained in:
bstr9 2024-06-26 22:26:20 +08:00 committed by GitHub
parent e4b17c40bf
commit afbcf4007a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
GPT_SoVITS/TTS_infer_pack/TTS.py
View File

@ -360,7 +360,11 @@ class TTS:
'''
self._set_prompt_semantic(ref_audio_path)
self._set_ref_spec(ref_audio_path)
self._set_ref_audio_path(ref_audio_path)
def _set_ref_audio_path(self, ref_audio_path):
self.prompt_cache["ref_audio_path"] = ref_audio_path
def _set_ref_spec(self, ref_audio_path):
audio = load_audio(ref_audio_path, int(self.configs.sampling_rate))
audio = torch.FloatTensor(audio)