Too much Latency!

Open owos opened this issue 1 year ago • 1 comments

I plan on using this for ASR spelling correction but the latency is too much for even the smallest model.

Is there a work around or potential solution for this?

Apr 24 '24 12:04 owos

I have problem installing elmo i'm using docker image https://hub.docker.com/layers/pytorch/pytorch/1.6.0-cuda10.1-cudnn7-runtime/images/sha256:9c3aa4653f6fb6590acf7f49115735be3c3272f4fa79e5da7c96a2c901631352 how could you run the code?

Apr 24 '24 13:04 Tarannom-sdgh