whisper ai on 1u server p100 or p40 or other <$300 used card?

Notice: Page may contain affiliate links for which we may earn a small commission through services like Amazon Affiliates or Skimlinks.

dinskuns

New Member
Nov 16, 2013
9
2
3
planning to transcribe the audio records of telephone calls, quite a good load (with up to 5 call records per minute),
budget for gpu up to around $300, xeon e5 server is 1u, no water cooling, can anyone recommend CUDA 11.7 or 11.8 (for pytorch) supported gpu to run whisper ai?
maybe i am missing some impoertant point here