backup/Realtime-Voice-Clone-Chinese
1
0
Fork 0
mirror of https://github.com/babysor/Realtime-Voice-Clone-Chinese.git synced 2026-04-14 18:40:31 +08:00
Code Issues Projects Releases Wiki Activity

Change default to use speaker embed for reference

Browse Source
This commit is contained in:
babysor
2021-11-13 10:57:45 +08:00
parent a37b26a89c
commit 7dca74e032
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
synthesizer/hparams.py
View File

@@ -92,5 +92,5 @@ hparams = HParams(
silence_min_duration_split = 0.4, # Duration in seconds of a silence for an utterance to be split
utterance_min_duration = 1.6, # Duration in seconds below which utterances are discarded
use_gst = True, # Whether to use global style token
use_ser_for_gst = False, # Whether to use speaker embedding referenced for global style token
use_ser_for_gst = True, # Whether to use speaker embedding referenced for global style token
)