Open RohitMidha23 opened 3 months ago
For those who might also face this same issue, the fix is to load faster_whisper models first and then the HuggingFace model. Not sure why that works.
Still facing this issue with other models. @trungkienbkhn any idea?
@RohitMidha23 , hello. Have you installed NVIDIA libraries (cuBLAS + cuDNN) for GPU ? Besides, could you show your full code ?
I get the following error when I run both, a huggingface model and a faster whisper model on the same GPU:
I am currently using a pipeline from huggingface, which is defined as follows:
It is not an OOM error as I'm able to load both of them separately and check memory usage!