whisper-large-v3-turbo-nepali-ctranslate2

This model is a CTranslate2 converted version of kiranpantha/whisper-large-v3-turbo-nepali.

This format is compatible with the faster-whisper library.

Usage with faster-whisper

from faster_whisper import WhisperModel

model = WhisperModel("kiranpantha/whisper-large-v3-turbo-nepali-ctranslate2", device="cuda", compute_type="float16")

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

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