Model reference · open weights
southern-kurdish-asr is an open-weight audio or speech model from aranemini. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | aranemini |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Parameters (lead) | 606M |
| Released | 2026-02-16 |
| Popularity | 512 downloads / month |
| Licence | Commercial licence needed |
About
Wav2Vec-BERT CTC model for Southern Kurdish (SDH) automatic speech recognition.
Southern Kurdish Part of Frezar benchmark
| Model | CER | WER |
|---|---|---|
| Wav2Vec-BERT CTC | 4.09 | 24.26 |
The model was trained and evaluated using resources developed for Southern Kurdish ASR.
Mohammadamini, Mohammad and Tahon, Marie. Southern Kurdish Speech Recognition Resources and Benchmarking. Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026).
@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"
}From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys southern-kurdish-asr for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (southern-kurdish-asr below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="southern-kurdish-asr" -F file=@audio.mp3
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.