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.

Repository from Github https://github.commozilla/DeepSpeechRepository from Github https://github.commozilla/DeepSpeech

how can I transform model file into an mmaped graph

fabianoluzbr opened this issue · comments

commented

hello guys, everytime i run my model i get this message: "Warning: reading entire model file into memory. Transform model file into an mmapped graph to reduce heap usage." But even searching here I didn't find a clear example of how to do this. And if it really makes a big difference in performance. Can anyone help me?