Orukeet
Orukeet is a 627M-parameter speech-to-text model from Oruk AI in the Orukeet / Parakeet-derived family, released under the CC BY-SA 4.0 license. The reviewed source lists 25 European languages (25 explicitly enumerated in our record), and the model is designed for batch-first transcription. Among the common setups we test, it ranks highest for long recordings on a mid-range NVIDIA GPU (#3 of 26 in the matcher).
September 2026 Parakeet-derived 627M recognizer covering the same 25 listed languages. Official releases include NeMo, ONNX INT8 and native Q8/F16 paths with segment timing. The open local model is batch-first rather than native incremental streaming. Weights are CC BY-SA 4.0: attribution and applicable ShareAlike obligations apply.
Key facts
| Provider | Oruk AI |
|---|---|
| Model family | Orukeet / Parakeet-derived |
| Parameters | 627M |
| License | CC BY-SA 4.0 · Attribution + ShareAlike — license text ↗ |
| Language coverage | 25 European languages · 25 enumerated in our record |
| Streaming | Batch-first (no streaming path in the reviewed source) |
| Timestamps | Yes — in the model or its runtime family |
| Speaker diarization | No — needs a separate component |
| Speech translation | No |
| Documented runtimes | orukeet package, NVIDIA NeMo, Hugging Face Transformers, sherpa-onnx — how to run it |
| Primary source | huggingface.co/oruk/orukeet ↗ |
| Last reviewed |
Hardware and workload fit
These are Speech Model Match's conservative 1–5 editorial ratings, relative to the other 19 reviewed models. They come from model size, official memory guidance and documented runtimes — not from a universal benchmark. How the ratings work.
| Dimension | Rating | Scale |
|---|---|---|
| CPU-only fit | 3/5 | |
| Apple Silicon fit | 4/5 | |
| NVIDIA GPU fit | 5/5 | |
| Speed | 5/5 | |
| Accuracy (relative) | 5/5 | |
| Low memory use | 3/5 | |
| Long recordings | 5/5 | |
| Live / low latency | 2/5 | |
| Subtitle work | 4/5 | |
| Edge / low-power devices | 3/5 |
Where it is strong
- Apple Silicon fit: rated 4/5
- NVIDIA GPU fit: rated 5/5
- Speed: rated 5/5
- Accuracy (relative): rated 5/5
- Long recordings: rated 5/5
- Subtitle work: rated 4/5
- Timestamps are available in the model or its runtime family
What to check first
- No streaming path in the reviewed source — plan for file/batch transcription
- Live / low latency: rated 2/5
- No native speaker diarization — pair it with a separate diarization pipeline if you need speaker labels
- Attribution and ShareAlike obligations apply to the model weights; review before modification or redistribution.
How it ranks in common setups
Ranks come from the same deterministic matcher that runs on the homepage, applied to all 26 reviewed models. They are decision guidance, not accuracy claims.
| Setup | Rank | Fit score | Top match |
|---|---|---|---|
| Long recordings on an 8–12 GB NVIDIA GPU, balanced | #3 of 26 | 79/100 · Strong fit | Whisper turbo |
| Live captions or voice input (native streaming + timestamps, speed first) | #19 of 26 | 66/100 · Possible fit | Nemotron 3.5 ASR Streaming 0.6B |
| Subtitles with timing, accuracy first | #5 of 26 | 83/100 · Strong fit | Whisper medium |
| Meetings with speaker labels (diarization + timestamps) | #5 of 26 | 84/100 · Strong fit | VibeVoice-ASR 7B |
| CPU-only machine, low memory use | #10 of 26 | 66/100 · Possible fit | VibeVoice-ASR-BitNet |
| Apple Silicon with 8–16 GB unified memory, long recordings | #10 of 26 | 69/100 · Possible fit | Whisper small |
| Japanese live transcription (native streaming, speed first) | Not ranked (language not listed) | — | Nemotron 3.5 ASR Streaming 0.6B |
Supported languages
- Bulgarian
bg - Croatian
hr - Czech
cs - Danish
da - Dutch
nl - English
en - Estonian
et - Finnish
fi - French
fr - German
de - Greek
el - Hungarian
hu - Italian
it - Latvian
lv - Lithuanian
lt - Maltese
mt - Polish
pl - Portuguese
pt - Romanian
ro - Russian
ru - Slovak
sk - Slovenian
sl - Spanish
es - Swedish
sv - Ukrainian
uk
Compare coverage across every reviewed model in the language support matrix.
Community activity on Hugging Face
- Downloads, last 30 days
- 33,850
- Likes
- 109
- Repository last updated
- 24 Sept 2026
- Published on the Hub
- 9 Sept 2026
Figures from the Hugging Face Hub API, 11 Nov 2026. Source: huggingface.co/oruk/orukeet ↗. Downloads count file downloads, not active users, and do not affect the matcher's scores. Compare all models.
How to run Orukeet locally
Orukeet ships its own installer that picks a runtime for your hardware; NeMo and Transformers exports are also published. Runtimes below are the ones the official model card or repository documents for this model (checked November 2, 2026).
- orukeet package ↗Official package · GGUF Q8/F16; picks Metal, CUDA or CPU automatically
- NVIDIA NeMo ↗Framework · .nemo source checkpoint
- Hugging Face Transformers ↗Framework · FP32 export
- sherpa-onnx ↗Third-party runtime · ONNX INT8 export listed on the card
Install command shown in the official huggingface.co page ↗:
python -m pip install --upgrade \
https://github.com/Oruk-AI/orukeet/releases/download/v0.1.1/orukeet-0.1.1-py3-none-any.whl
orukeet install --device auto --cache ./orukeet-cache --output installation.json
Official hardware guidance: No RAM or VRAM figure is published. Download sizes: Q8 GGUF about 714 MB, F16 GGUF about 1.3 GB. Source ↗
Repository code is MIT; the weights are CC BY-SA 4.0 and keep NVIDIA's attribution.
Whatever runtime you choose, measure speed and accuracy on your own audio with the benchmark tool; results differ a lot between runtimes, precision and hardware.
Before you deploy Orukeet
A printable checklist built from the facts on this page. Tick it off before putting the model into production.
- Language. Confirm your language is in the 25-language list on this page, and test any accents or code-switching you expect.
- License. CC BY-SA 4.0: Everything CC BY requires, plus: adaptations you share must be licensed under CC BY-SA 4.0 or a BY-SA compatible license. License guide.
- Install. Start from the official command:
python -m pip install --upgrade \ …(full run notes). - Audio input. Convert a sample of your real recordings to the format the runtime expects before benchmarking.
- Hardware. No RAM or VRAM figure is published. Download sizes: Q8 GGUF about 714 MB, F16 GGUF about 1.3 GB.
- Features you rely on. For Orukeet, no streaming path is documented; timestamps are documented; speaker labels need a separate diarization component. Test each one you need with real audio.
- Measure. Run 10–20 representative clips, score them with the WER calculator and record speed in the benchmark workspace before you commit.
Alternatives and related models
Similar fit profile: Omnilingual ASR CTC 300M (Meta AI, 325M), Parakeet TDT 0.6B v3 (NVIDIA, 600M), Distil-Whisper large-v3 (Hugging Face / Distil-Whisper, large-v3 distilled). Similarity is computed from the ten fit ratings plus streaming and diarization support.
| Fact | Orukeet | Omnilingual ASR CTC 300M | Parakeet TDT 0.6B v3 |
|---|---|---|---|
| Provider · size | Oruk AI · 627M | Meta AI · 325M | NVIDIA · 600M |
| License | CC BY-SA 4.0 Attribution + ShareAlike | Apache-2.0 Permissive | CC BY 4.0 Attribution required |
| Languages | 25 European languages | 1,600+ language codes | 25 European languages |
| Streaming | Batch-first | Batch-first | Via runtime |
| Timestamps | Yes | Limited | Yes |
| Speaker diarization | Separate pipeline | Separate pipeline | Separate pipeline |
| CPU · Apple · NVIDIA fit | 3/5 · 4/5 · 5/5 | 3/5 · 4/5 · 5/5 | 2/5 · 3/5 · 5/5 |
| Live · long recordings | 2/5 · 5/5 | 2/5 · 3/5 | 2/5 · 5/5 |
| Main runtime | orukeet package | omnilingual-asr package | NVIDIA NeMo |
Head-to-head pages: Parakeet TDT 0.6B v3 vs Orukeet
Guides that cover Orukeet
- Best local speech-to-text models in 2026
- Best local Whisper alternatives in 2026
- Best local speech-to-text models for multilingual use
Check Orukeet for your setup
Pick your language, hardware and workload to see this model's fit score, the reasons behind it and where it ranks against all reviewed models. Everything runs in your browser.
Common questions
Can I use Orukeet commercially?
Attribution and ShareAlike obligations apply to the model weights; review before modification or redistribution. The listed license is CC BY-SA 4.0; read the current license text ↗ before shipping a product, because terms can change. The license guide compares the obligations of all 26 reviewed models.
Does Orukeet support real-time streaming?
No streaming path is documented in the reviewed source. Treat it as a file/batch transcription model.
Which languages does Orukeet transcribe?
25 European languages. The full list of 25 explicitly enumerated languages is shown above.
Can Orukeet tell speakers apart?
Not natively. Combine it with a dedicated diarization component and evaluate that component separately; the meetings guide covers this workflow.
Primary sources
Reviewed against primary sources on September 16, 2026. Model behavior, runtime support, language coverage and licenses can change; re-check the linked primary source before production use. See the full source directory.