Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix(freevc): use the specified device for pretrained speaker encoder (#45) 

Fixes coqui-ai#3787
This commit is contained in:
ChristianRomberg 2024-06-16 21:24:03 +02:00 committed by GitHub
parent 063e9e9de9
commit 3a20f4725f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
TTS/vc/models/freevc.py
View File

@ -382,7 +382,8 @@ class FreeVC(BaseVC):
"""Load pretrained speaker encoder model as mentioned in the paper."""
logger.info("Loading pretrained speaker encoder model ...")
self.enc_spk_ex = SpeakerEncoderEx(
"https://github.com/coqui-ai/TTS/releases/download/v0.13.0_models/speaker_encoder.pt"
"https://github.com/coqui-ai/TTS/releases/download/v0.13.0_models/speaker_encoder.pt",
device=self.device
)
def init_multispeaker(self, config: Coqpit):