Hi, I try to install CrisperWhisper using its faster-whisper variant.
CUDA = 12.4.0
ctranslate2==4.6.0
faster-whisper=1.1.1
torch==2.5.1+cu124.post3
torchaudio==2.5.1
torchvision==0.20.1+cu124torch251
I am using virtualenv for Python 3.11.5
This is the error I get:
self.model = ctranslate2.models.Whisper(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: This CTranslate2 package was not compiled with CUDA support
Code I'm using:
from faster_whisper import WhisperModel
from datasets import load_dataset
import torch
faster_whisper_model = 'nyrahealth/faster_CrisperWhisper'
# Initialize the Whisper model
device = "cuda" if torch.cuda.is_available() else "cpu"
torch_dtype = "float16" if torch.cuda.is_available() else "float32"
model = WhisperModel(faster_whisper_model, device=device, compute_type=torch_dtype)
dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
sample = dataset[0]["audio"]
segments, info = model.transcribe(sample['array'], beam_size=1, language='en', word_timestamps = True, without_timestamps= True)
for segment in segments:
print(segment)
Thanks in advance