adalat-ai/ct2-whisper-medium-reverse-ml-mft-2-2-2

CTranslate2 Version of whisper-medium-reverse-ml-mft-2-2-2

This is a CTranslate2 port of the original model.

Usage with faster-whisper

from faster_whisper import WhisperModel

model = WhisperModel('./ct2-models/ct2-whisper-medium-reverse-ml-mft-2-2-2', device='cuda', compute_type='float16')
segments, info = model.transcribe('audio.mp3')

for segment in segments:
    print(f'{segment.start:.2f} - {segment.end:.2f}: {segment.text}')