run transcribe.py over gpu

mozilla / DeepSpeech

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

Mozilla Public License 2.0

25.44k stars 3.98k forks source link

run transcribe.py over gpu #3719

Closed ros-packages closed 2 years ago

ros-packages commented 2 years ago

Hello I want to transcribe a large number of files with deepspeech and I want to use Tensorflow but apparently, transcribe.py does not use GPU and it fills all my CPU cores. Is there a way for transcribe.py to use GPU? Is there any way to run pb file instead of checkpoints in transcribe.py? thanks.

JRMeyer commented 2 years ago

Take a look at issue https://github.com/mozilla/DeepSpeech/issues/3693