You can deploy this model and start earning money today!

RsGoksel/
RsGoksel_ITU_Mainframe-balanced-ct2

Name: RsGoksel_ITU_Mainframe-balanced-ct2
Availability: InStock

automatic-speech-recognition

openai/whisper-large-v3-turbo

finetune

mit

Views

No views yet

RsGoksel_ITU_Mainframe-balanced-ct2

Türkçe ASR — openai/whisper-large-v3-turbo üzerine LoRA fine-tune. Çok-domain dengeli all-rounder (clean + robustluk + medikal birlikte korunur). CTranslate2 (float16) derlemesi — faster-whisper / WhisperX ile hızlı çıkarım.

Hızlı kullanım — faster-whisper

python

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

WhisperX ile

python

import whisperx
m = whisperx.load_model("RsGoksel/RsGoksel_ITU_Mainframe-balanced-ct2", device="cuda", compute_type="float16",
                        language="tr", asr_options={"condition_on_previous_text": False})
res = m.transcribe("audio.wav", language="tr")
text = " ".join(s["text"] for s in res["segments"])

Önerilen: language="tr", condition_on_previous_text=False. Metrik: Türkçe normalizasyon sonrası mean-per-utterance WER.

Tam-hassasiyet (transformers) sürümü: RsGoksel/RsGoksel_ITU_Mainframe-balanced.