Open JohnXLivingston opened 2 months ago
I don't think we can limit RAM but CPU yes there is a threads
option
--threads THREADS number of threads used for CPU inference (default: 0)
RAM usage largely depends on model size since it must be loaded to RAM (multiplied by the number of runners since models aren't shared in memory).
For example with whisper-ctranslate2
(which uses faster-whisper
which is CPU friendly) the models tend to be larger than the one provided for openai-whisper
:
large-v3
~3GBmedium
~1.5GBtiny
~75MBOf course, transcript quality will get worse the further you decrease the size.
Thanks for the information @lutangar ! Good to know.
Describe the problem to be solved
v6.2.0-RC1 comes with an incredible feature: automatic subtitles generation.
But the models that are used can use a lot of CPU and RAM. I did not see any option to limit their usage (as we can with video transcoding).
Describe the solution you would like
Would it be possible to add some options?