nvidia/nemotron-3.5-asr-streaming-0.6b (FastConformer-CacheAware RNNT, 638M) fine-tuned for Slovenian on ARTUR (858 h) + Common Voice — a low-latency streaming model that works across read and spontaneous speech. Runs on GPU via NeMo or on CPU via parakeet.cpp (GGUF).

Results (WER, normalized, held-out)

Test set	WER
Common Voice sl	25.07%
ARTUR multi-domain	23.42%
ARTUR parliamentary (spontaneous)	21.66%
FLEURS sl	33.07%

Comparison — vs `yuriyvnv/parakeet-tdt-0.6b-slovenian`

Different design goals; honest numbers (normalized WER):

Test set	This model (streaming)	parakeet-tdt-0.6b-slovenian (non-streaming)
FLEURS sl	33.07%	17.74%
Common Voice sl	25.07%	8.81%
ARTUR parliamentary (spontaneous)	21.66%	not reported

parakeet-tdt is better on clean read speech — stronger non-streaming base (parakeet-tdt-0.6b-v3), trained on read data (Common Voice + synthetic TTS).
This model is a streaming (real-time, low-latency, CPU-deployable) model trained on 858 h ARTUR + Common Voice, so it stays robust on spontaneous/conversational speech (parliamentary ~22%) — a domain read-only models don't target. (CV test differs slightly: CV26 here vs CV17 there.)

Pick by use case: read-speech accuracy → parakeet-tdt; real-time streaming + spontaneous speech → this model.

Files

nemotron_sl.nemo — NeMo checkpoint (GPU inference / further fine-tuning)
asr_sl_v3.gguf (q8_0) — parakeet.cpp CPU inference

How to run

bash

# CPU, streaming, via parakeet.cpp — use lang tag sl-SI, 16 kHz mono
parakeet-cli --model asr_sl_v3.gguf --lang sl-SI audio.wav

python

# GPU via NeMo
from nemo.collections.asr.models import ASRModel
m = ASRModel.restore_from("nemotron_sl.nemo")
m.transcribe(["audio.wav"])   # 16 kHz mono; manifest lang/target_lang = "sl-SI"

License & data provenance

Released CC BY-SA 4.0 (to honor the ARTUR ShareAlike terms).

Input	License
Base `nvidia/nemotron-3.5-asr-streaming-0.6b`	OpenMDW-1.1 (retain NOTICE)
ARTUR 1.0 (CLARIN.SI, 858 h)	CC BY-SA 4.0 (attribution + ShareAlike)
Common Voice sl	CC0

Credit CLARIN.SI (ARTUR: hdl.handle.net/11356/1776 audio, /11356/1772 transcriptions), NVIDIA, and Mozilla Common Voice.

Citation

Cite this work (Tadej Fius, MediaAtlas Ltd):

bibtex

@misc{fius2026asr,
  title        = {Nemotron-3.5 Slovenian Streaming ASR},
  author       = {Fius, Tadej},
  year         = {2026},
  publisher    = {MediaAtlas Ltd},
  howpublished = {Hugging Face},
  url          = {https://huggingface.co/texdata/nemotron-3.5-asr-streaming-slovenian}
}

Upstream / source citations:

bibtex

@misc{nemotron_asr, title={Nemotron-3.5 ASR Streaming 0.6B (FastConformer-CacheAware RNNT)}, author={{NVIDIA}}, url={https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b}}
@article{kuchaiev2019nemo, title={NeMo: a toolkit for building AI applications using Neural Modules}, author={Kuchaiev, O. and others}, journal={arXiv:1909.09577}, year={2019}}
@misc{artur, title={ARTUR: Speech Database of Slovene}, author={{CLARIN.SI}}, note={audio hdl:11356/1776, transcriptions hdl:11356/1772}, url={http://hdl.handle.net/11356/1776}}

Base under OpenMDW-1.1 (retain NOTICE). Data: ARTUR (CLARIN.SI); credit NVIDIA + CLARIN.SI.

texdata/nemotron-3.5-asr-streaming-slovenian

Slovenian streaming ASR — Nemotron-3.5 fine-tune (v3)