aranemini/southern-kurdish-asr

Southern Kurdish ASR

Wav2Vec-BERT CTC model for Southern Kurdish (SDH) automatic speech recognition.

Model Description

• Language: Southern Kurdish (SDH)
• Architecture: Wav2Vec-BERT 2.0 CTC
• Training data: 30 hours of validated read speech
• Task: Automatic Speech Recognition

Evaluation

Southern Kurdish Part of Frezar benchmark

Model	CER	WER
Wav2Vec-BERT CTC	4.09	24.26

Dataset

The model was trained and evaluated using resources developed for Southern Kurdish ASR.

Southern Kurdish ASR Dataset

Paper

Mohammadamini, Mohammad and Tahon, Marie. Southern Kurdish Speech Recognition Resources and Benchmarking. Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026).

Paper

Citation

@inproceedings{mohammadamini-tahon-2026-southern,
  title = "Southern Kurdish Speech Recognition Resources and Benchmarking",
  author = "Mohammadamini, Mohammad and Tahon, Marie",
  booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
  year = "2026",
  pages = "5538--5544",
  doi = "10.63317/2rkqhw7hmo2d"
}