faster-whisper-large-v3-turbo-turkish

This model is a CTranslate2 conversion of selimc/whisper-large-v3-turbo-turkish, optimized for fast inference with faster-whisper.

The original model is a fine-tuned version of OpenAI Whisper Large V3 Turbo, trained on the Mozilla Common Voice 17.0 dataset for Turkish speech recognition.

Model Details

• Original Model: selimc/whisper-large-v3-turbo-turkish
• Format: CTranslate2 (float16)
• Size: ~1.6GB
• Language: Turkish

Usage

Compatible with faster-whisper and any CTranslate2-based project such as Open WebUI.

from faster_whisper import WhisperModel

model = WhisperModel("vincespeed/faster-whisper-large-v3-turbo-turkish",
                     device="cuda",
                     compute_type="float16")

segments, info = model.transcribe("audio.wav", language="tr")

for segment in segments:
    print(segment.text)

Acknowledgements

All credit for the original training goes to selimc. This repository only provides a CTranslate2 conversion for faster inference.