End-to-End Transformer-based Automatic Speech Recognition for Northern Kurdish: A Pioneering Approach

TL;DR

This paper evaluates the effectiveness of Whisper, a pre-trained transformer-based model, for Northern Kurdish ASR, demonstrating that specialized fine-tuning significantly improves accuracy on low-resource language data.

Contribution

It introduces a fine-tuning approach for Whisper on Northern Kurdish, showing that additional module tuning enhances ASR performance for low-resource languages.

Findings

Achieved WER of 10.5% and CER of 5.7% on Northern Kurdish ASR.

Demonstrated the effectiveness of additional module fine-tuning strategies.

Highlighted the potential of transformer models for low-resource language ASR.

Abstract

Automatic Speech Recognition (ASR) for low-resource languages remains a challenging task due to limited training data. This paper introduces a comprehensive study exploring the effectiveness of Whisper, a pre-trained ASR model, for Northern Kurdish (Kurmanji) an under-resourced language spoken in the Middle East. We investigate three fine-tuning strategies: vanilla, specific parameters, and additional modules. Using a Northern Kurdish fine-tuning speech corpus containing approximately 68 hours of validated transcribed data, our experiments demonstrate that the additional module fine-tuning strategy significantly improves ASR accuracy on a specialized test set, achieving a Word Error Rate (WER) of 10.5% and Character Error Rate (CER) of 5.7% with Whisper version 3. These results underscore the potential of sophisticated transformer models for low-resource ASR and emphasize the importance of tailored fine-tuning techniques for optimal performance.