# Breaking Walls: Pioneering Automatic Speech Recognition for Central Kurdish: End-to-End Transformer Paradigm

arXiv: https://arxiv.org/abs/2406.02561 · HTML: https://mlsanity.com/paper/2406.02561/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2024.

## Built on by (most cited first, 7 of 7)

- [Advanced Clustering Techniques for Speech Signal Enhancement: A Review and Metanalysis of Fuzzy C-Means, K-Means, and Kernel Fuzzy C-Means Methods](https://mlsanity.com/paper/2409.19448/) (2024)
- [From Dialect Gaps to Identity Maps: Tackling Variability in Speaker Verification](https://mlsanity.com/paper/2505.04629/) (2025)
- [Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach](https://mlsanity.com/paper/2409.13734/) (2024)
- [End-to-End Transformer-based Automatic Speech Recognition for Northern Kurdish: A Pioneering Approach](https://mlsanity.com/paper/2410.16330/) (2024)
- [Speaker Diarization for Low-Resource Languages Through Wav2vec Fine-Tuning](https://mlsanity.com/paper/2504.18582/) (2025)
- [Which one Performs Better? Wav2Vec or Whisper? Applying both in Badini Kurdish Speech to Text (BKSTT)](https://mlsanity.com/paper/2508.09957/) (2025)
- [KurdSTS: The Kurdish Semantic Textual Similarity](https://mlsanity.com/paper/2510.02336/) (2025)

## Abstract (arXiv)

End-to-end transformer-based models epitomize the cutting-edge in Automatic Speech Recognition (ASR) systems. Despite their substantial benefits, these models demand extensive training data to perform optimally, presenting a significant challenge for low-resource languages such as Central Kurdish. Addressing this issue requires innovative methods and techniques. This paper aims to develop an ASR system for Intermediate Kurdish by collecting a robust corpus of speech, using the N-GRAM language model, and utilizing an external Kurdish tokenizer for refinement and integration techniques to enhance the model's performance. We collect a comprehensive 100-hour speech corpus from diverse sources. Additionally, applied fine-tuning techniques to our speech corpus on Persian, English, and Arabic pre-trained models, specifically utilizing the xls-r-300m, xls-r-1b, and xls-r-2b Wav2vec 2.0 models. And utilized language models trained by 3-gram and 4-gram from a large text corpus of 300 million tokens. The fine-tuned xls-r-2b model, combined with a 3-gram language model and included external Kurdish tokenizer, achieved the best performance, yielding a Word Error Rate (WER) of 10.0% on the validation set and 11.8% on the Asosoft test set. The ASR model has demonstrated the advantages of having a large vocabulary compared to the existing Kurdish ASR models. Compared to other models, it produced more accurate and higher performance outcomes by working with a lower error rate.