SagyHarpazGong
SagyHarpazGong
Hi all. I have audio with duration of about 90 minutes and it contains 8 speakers, when I'm running the MSDD I'm getting only 4 speakers. Some of the speakers...
I'm trying to run model server using kserve but I'm getting the following error: ``` Traceback (most recent call last): File "/project/e2e_servers/pre_asr_kserve.py", line 215, in ModelServer(http_port=8000).start({'PRE-ASR': PreASRServer}) File "/home/xxx/.conda/envs/my_env/lib/python3.9/site-packages/kserve/model_server.py", line...
I run the MSDD model on Nvidia A10 (24GB), but the inference is too slow, I looked on the code and there is a lot of traffic between the CPU...