RsGoksel_ITU_Mainframe-ct2 — CTranslate2 / faster-whisper build

CTranslate2 (float16) conversion of RsGoksel/RsGoksel_ITU_Mainframe, a Turkish LoRA fine-tune of openai/whisper-large-v3-turbo (codename VH5.0d). For full results, training details, and the data/license statement, see the main repo.

from faster_whisper import WhisperModel
model = WhisperModel("RsGoksel/RsGoksel_ITU_Mainframe-ct2", device="cuda", compute_type="float16")
segments, _ = model.transcribe("audio.wav", language="tr", beam_size=5, vad_filter=True)
print(" ".join(s.text for s in segments))

License: CC-BY-NC-4.0 (research / non-commercial). The fine-tuning corpus includes provenance-unclear and non-commercial sources — see the main repo's data statement.