Unknown bug - restarting Kernel - probably GPU issue

[beastraban]

Hi,

I am using faster-whisper out of the box with the following code (as suggested in the readme):

from faster_whisper import WhisperModel
import logging

logging.basicConfig()
logging.getLogger("faster_whisper").setLevel(logging.DEBUG)

model_size = "large-v3"
model = WhisperModel(model_size, device="cuda", compute_type="float16")

`segments,` info = model.transcribe("audio.mp3", beam_size=5)

print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

My output is the following:

C:\Users\irawo\.conda\envs\Faster\lib\site-packages\tqdm\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm
INFO:faster_whisper:Processing audio with duration 42:57.517

Restarting kernel...

On device='cpu',
compute_type="int8"

it works fine but very slow. How would I go about connecting my GPU?

I am working with anaconda on windows with RTX3080 32Gb python version 3.10

[phineas-pta]

u install cuda properly ?