search

mozilla / TTS

:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
Mozilla Public License 2.0
9.27k stars 1.24k forks source link

Garbage Collection issue #746

Closed MultiTrickFox closed 2 years ago

MultiTrickFox commented 2 years ago

My code is simple: (nothing out of the ordinary)

wav, alignment, , = synthesis( model, sentence, voice_config, use_gpu, # -> false. voice_processor, speaker_id = None, d_vector = my_dvector, style_wav = None, language_id = 0, enable_eos_bos_chars = voice_config.enable_eos_bos_chars, use_griffin_lim = True, do_trim_silence = False, ).values()

I notice that after running this code multiple times (in a loop), the next runs always add on to the memory (tested on ubuntu latest and osx). I could post the memory screenshots here but it is trivial to observe. How could I overcome this? Any help would be appreciated, thank you..

JRMeyer commented 2 years ago

you should take a look at #745

stale[bot] commented 2 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. You might also look our discourse page for further help. https://discourse.mozilla.org/c/tts