Qwen3-ASR-1.7B Norwegian 2306
Kushtrim/Qwen3-ASR-1.7B-Norwegian-2306 is a Norwegian automatic speech
recognition checkpoint fine-tuned from
Qwen/Qwen3-ASR-1.7B.
The model is intended for general Norwegian speech-to-text experiments. It
retains the Qwen3-ASR architecture and can be used through the qwen-asr
toolkit.
It is trained on a couple thousand well-curated hours of Norwegian audio and transcripts.
Model details
| Property | Value |
|---|---|
| Task | Automatic speech recognition |
| Language | Norwegian |
| Base model | Qwen3-ASR-1.7B |
| Architecture | Qwen3ASRForConditionalGeneration |
| Saved precision | BF16 |
| Audio feature size | 128 |
| Saved training step | 152,676 |
| Recorded epoch | 2.258 |
| Per-device training batch size | 16 |
The saved trainer state contains no evaluation history, so this card does not claim a WER or other benchmark score.
Usage
pip install -U qwen-asr
import torch
from qwen_asr import Qwen3ASRModel
model = Qwen3ASRModel.from_pretrained(
"Kushtrim/Qwen3-ASR-1.7B-Norwegian-2306",
dtype=torch.bfloat16,
device_map="cuda:0",
max_inference_batch_size=32,
max_new_tokens=256,
)
results = model.transcribe(
audio="path/to/audio.wav",
language="Norwegian",
)
print(results[0].text)
For automatic language identification, set language=None.
Intended use
- Norwegian audio transcription and ASR research.
- Comparison with the base Qwen3-ASR model and other Norwegian checkpoints.
- Further fine-tuning or domain adaptation where the base-model license allows.
Limitations
- No benchmark results are currently documented for this checkpoint.
- Accuracy may vary across Bokmål, Nynorsk, dialects, recording conditions, background noise, and specialized vocabulary.
- Generated transcripts can contain omissions, substitutions, or invented words. Human review is recommended for consequential use.
- Evaluate the model on representative audio before deployment.
Provenance
The architecture, precision, training step, epoch, and batch size above were recovered from the repository's saved configuration and trainer state. Add the training datasets, preprocessing decisions, and evaluation results here when they are available.
Development and attribution
- Original architecture and base weights: Qwen Team, through
Qwen/Qwen3-ASR-1.7B - Norwegian adaptation, fine-tuning, training-data curation, checkpoint preparation, packaging, and release: Kushtrim Visoka
- Model card and ongoing maintenance: Kushtrim Visoka
Acknowledgements
This work builds on Qwen3-ASR by the Qwen team. The original architecture and base weights remain the work of their respective authors. This repository documents the Norwegian fine-tuning and release work carried out by Kushtrim Visoka and does not claim authorship of the original Qwen3-ASR model.
Citation
If you use this fine-tuned model, please cite this repository and the original Qwen3-ASR model.
@misc{visoka_qwen3_asr_17b_norwegian_2306_2026,
author = {Visoka, Kushtrim},
title = {Qwen3-ASR-1.7B Norwegian 2306},
year = {2026},
publisher = {Hugging Face},
url = {https://huggingface.co/Kushtrim/Qwen3-ASR-1.7B-Norwegian-2306},
note = {Fine-tuned from Qwen/Qwen3-ASR-1.7B}
}