I'm running on NVIDA GPU.
I installed this package via:
WHISPER_CUDA=1 pip install git+https://github.com/abdeladim-s/pywhispercpp
I run the following code:
from pywhispercpp.model import Model
model = Model("small.en")
segments = model.transcribe(r"common_voice_en_2925.wav")
and it doesn't use the GPU.
How can we run pywhispercpp on GPU ?