from faster_whisper import WhisperModel
from datasets import load_dataset
faster_whisper_model = "nyrahealth/faster_CrisperWhisper"

Initialize the Whisper model

device = "cuda:0" 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="float32")
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)