Hello, here is my dockerfile :
FROM nvidia/cuda:12.3.2-cudnn9-runtime-ubuntu22.04
RUN apt-get update -y && apt-get install -y python3 python3-pip
RUN python3 -m pip install pip --upgrade
RUN pip3 install faster-whisper
RUN mkdir /app
WORKDIR /app
COPY app /app
ENTRYPOINT ["python3", "main.py"]
and when i call the transcribe method in my python file, i have the following issue :
Traceback (most recent call last):
File "/app/main.py", line 26, in <module>
model = WhisperModel(model_name, device=device, compute_type=compute_type)
File "/usr/local/lib/python3.10/dist-packages/faster_whisper/transcribe.py", line 689, in __init__
self.model = ctranslate2.models.Whisper(
ValueError: This CTranslate2 package was not compiled with CUDA support
what am i doing wrong?