no1d

Results 2 issues of no1d

I'm experimenting around with the server on Windows and it works fine using CPU. But with CUDA it crashes after a client disconnects. _Seems like the speech-to-text thread doesn't die...

Tried https://github.com/OpenNMT/CTranslate2/pull/1201 with no luck, so this should fix https://github.com/SYSTRAN/faster-whisper/issues/71