forked from mrq/tortoise-tts
Merge pull request #36 from e0xextazy/main
Optimizing graphics card memory
This commit is contained in:
commit
5c60c5d4f2
|
@ -225,6 +225,7 @@ class TextToSpeech:
|
||||||
properties.
|
properties.
|
||||||
:param voice_samples: List of 2 or more ~10 second reference clips, which should be torch tensors containing 22.05kHz waveform data.
|
:param voice_samples: List of 2 or more ~10 second reference clips, which should be torch tensors containing 22.05kHz waveform data.
|
||||||
"""
|
"""
|
||||||
|
with torch.no_grad():
|
||||||
voice_samples = [v.to('cuda') for v in voice_samples]
|
voice_samples = [v.to('cuda') for v in voice_samples]
|
||||||
|
|
||||||
auto_conds = []
|
auto_conds = []
|
||||||
|
|
Loading…
Reference in New Issue
Block a user