Whisper Kurmanji - RojMusic

This model is a fine-tuned version of openai/whisper-base on a vast custom dataset of 90,000 Kurmanji Kurdish audio files. It was developed to bring state-of-the-art automatic speech recognition (ASR) to the Kurmanji dialect, making it accessible for global companies, researchers, and developers.

Usage

from transformers import pipeline

transcriber = pipeline("automatic-speech-recognition", model="RojMusic/whisper-kurmanji-rojmusic")
result = transcriber("your_kurdish_audio_file.wav")
print(result["text"])

Training Data

This model was fine-tuned on a highly curated dataset consisting of 90,000 Kurmanji audio samples, including music lyrics, speech, and cultural recordings.

Acknowledgements

Trained via the RojMusic AI Platform.