Hi guys, there seems to be a memory leak in the python sdk for streaming. If you are transcribing audio it stores all audio sent to the service in memory which is less than ideal obviously. Only workaround for me was to manually recreate the service periodically. I have now moved to using the Java version instead and experience no issues. Cheers, good luck.
Hi guys, there seems to be a memory leak in the python sdk for streaming. If you are transcribing audio it stores all audio sent to the service in memory which is less than ideal obviously. Only workaround for me was to manually recreate the service periodically. I have now moved to using the Java version instead and experience no issues. Cheers, good luck.