LeonidWang

> Solution for 16xx card owners, which is worked for me: > > 1. Download cudnn libraries from NVIDIA site, version > 8.2.0 (I have tested 8.5.0.96 and 8.3.3.40) >...

I can confirm this still exists in the latest image pulled from DockerHub. Image built from current master version also got this. The docker image I built got this error...

[Edit] I stand corrected. After running v1.7.14 longer, I hit the issue again, but looks this time there's no 'signal 15' in the log, issue started from 'org.apache.coyote.AbstractProtocol.pause Pausing ProtocolHandler'...

Doesn't work for me. For those who still have problems, see issue #231 , it can be installed in Pytorch2.0+ with C++17. https://github.com/WayenVan/ctcdecode